Face videos accompanied by audio have become integral to our daily lives, while they often suffer from complex degradations. Most face video restoration methods neglect the intrinsic correlations between visual and audio features, particularly in the mouth region. Several audio-aided face video restoration methods have been proposed, but they only focus on compression artifact removal. In this paper, we propose a General Audio-assisted face Video restoration Network (GAVN) to address various types of streaming video distortions via identity and temporal complementary learning. Specifically, GAVN first captures inter-frame temporal features in the low-resolution space to restore frames coarsely and save computational cost. Then, GAVN extracts intra-frame identity features in the high-resolution space with the assistance of audio signals and face landmarks to restore more facial details. Finally, the reconstruction module integrates temporal features and identity features to generate high-quality face videos. Experimental results demonstrate that GAVN outperforms the existing state-of-the-art methods on face video compression artifact removal, deblurring, and super-resolution.

Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment. Quantization offers a potential solution for compressing the VSR model. Nevertheless, quantizing VSR models is challenging due to their temporal characteristics and high fidelity requirements. To address these issues, we propose QuantVSR, a low-bit quantization model for real-world VSR. We propose a spatio-temporal complexity aware (STCA) mechanism, where we first utilize the calibration dataset to measure both spatial and temporal complexities for each layer. Based on these statistics, we allocate layer-specific ranks to the low-rank full-precision (FP) auxiliary branch. Subsequently, we jointly refine the FP and low-bit branches to achieve simultaneous optimization. In addition, we propose a learnable bias alignment (LBA) module to reduce the biased quantization errors. Extensive experiments on synthetic and real-world datasets demonstrate that our method obtains comparable performance with the FP model and significantly outperforms recent leading low-bit quantization methods.

Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from over-reliance on generative priors. To address these issues, we propose SODEC, a novel single-step diffusion image compression model. We argue that in image compression, a sufficiently informative latent renders multi-step refinement unnecessary. Based on this insight, we leverage a pre-trained VAE-based model to produce latents with rich information, and replace the iterative denoising process with a single-step decoding. Meanwhile, to improve fidelity, we introduce the fidelity guidance module, encouraging output that is faithful to the original image. Furthermore, we design the rate annealing training strategy to enable effective training under extremely low bitrates. Extensive experiments show that SODEC significantly outperforms existing methods, achieving superior rate-distortion-perception performance. Moreover, compared to previous diffusion-based compression models, SODEC improves decoding speed by more than 20×.

JPEG, as a widely used image compression standard, often introduces severe visual artifacts when achieving high compression ratios. Although existing deep learning-based restoration methods have made considerable progress, they often struggle to recover complex texture details, resulting in over-smoothed outputs. To overcome these limitations, we propose SODiff, a novel and efficient semantic-oriented one-step diffusion model for JPEG artifacts removal. Our core idea is that effective restoration hinges on providing semantic-oriented guidance to the pre-trained diffusion model, thereby fully leveraging its powerful generative prior. To this end, SODiff incorporates a semantic-aligned image prompt extractor (SAIPE). SAIPE extracts rich features from low-quality (LQ) images and projects them into an embedding space semantically aligned with that of the text encoder. Simultaneously, it preserves crucial information for faithful reconstruction. Furthermore, we propose a quality factor-aware time predictor that implicitly learns the compression quality factor (QF) of the LQ image and adaptively selects the optimal denoising start timestep for the diffusion process. Extensive experimental results show that our SODiff outperforms recent leading methods in both visual quality and quantitative metrics.

Federated learning (FL) has advanced semantic segmentation through decentralized training to reduce annotation costs. However, most FL-based semantic segmentation methods assume fixed foreground classes, resulting in catastrophic forgetting of old categories when local clients continually collect streaming data of new classes without storing old categories. Moreover, the irregular participation of new local clients with novel classes unseen by others may exacerbate heterogeneous forgetting across clients during global FL training. To resolve the above challenges, we propose a Hierarchical Forgetting Alleviation (HFA) model. By tackling forgetting within and across local clients, our model ensures that all local clients learn from each other as they continuously learn new categories. Specifically, to alleviate class-imbalanced forgetting within local clients induced by background shift, we develop a confidence-regularized pseudo labeling strategy to produce class-balanced soft pseudo labels for old categories that are labeled as background. Guided by soft pseudo labels, we design a graph-induced relation matching loss and a forgetting-balanced gradient propagation module to tackle ambiguous inter-class relations and class-imbalanced gradient propagation among old classes. Besides, a novel task detection module and an adaptive DBSCAN clustering are devised to address inter-client heterogeneous forgetting. They detect the arrival of new tasks to store the old global model for local pseudo labeling and distillation, while supplying global class prototypes for modeling inter-class relations and warm-starting global classifier. Experiments on multiple datasets verify our model's superiority over other methods.

Despite the recent advances in the application of diffusion models to the realm of image restoration, their inherent stochastic nature can often lead to inaccuracies in reconstructing spatial structures and fine details. This paper introduces an innovative paradigm that harnesses the rich knowledge encapsulated in existing high-level pre-trained models to guide the diffusion process, offering a flexible and potent approach to restoration tasks. However, there are significant challenges in leveraging a pre-trained model for image restoration, including a data gap between natural clean images and degradation images, and paradigm differences that cause insufficient intermediate knowledge. To tackle these issues, we introduce informative Messenger prompts and a Self-adapter for the pre-trained model, whose appropriate information acts as explicit constraints for diffusion, enabling reliable result generation. Specifically, ourMeSa-IRsuccessfully adapts to feature exploration for degraded samples, via disseminating distinctive information from degraded instances. Furthermore, it bolsters knowledge representation through the bidirectional interchange of hierarchical information facilitated by the innovative use of messenger prompts. Experimental results demonstrate the state-of-the-art performance of our framework on five tasks in terms of perceptual and distortion metrics. We will release codes at https://github.com/Ephemeral182/MeSa-IR.

In the coded aperture snapshot spectral imaging system, Deep Unfolding Networks (DUNs) have made impressive progress in recovering 3D hyperspectral images (HSIs) from a single 2D measurement. However, the inherent nonlinear and ill-posed characteristics of HSI reconstruction still pose challenges to existing methods in terms of accuracy and stability. To address this issue, we propose a Mamba-inspired Joint Unfolding Network (MiJUN), which integrates physics-embedded DUNs with learning-based HSI imaging. Firstly, leveraging the concept of trapezoid discretization to expand the representation space of unfolding networks, we introduce an accelerated unfolding network scheme. This approach can be interpreted as a generalized accelerated half-quadratic splitting with a second-order differential equation, which reduces the reliance on initial optimization stages and addresses challenges related to long-range interactions. Crucially, within the Mamba framework, we restructure the Mamba-inspired global-to-local attention mechanism by incorporating a selective state space model and an attention mechanism. This effectively reinterprets Mamba as a variant of the Transformer architecture, improving its adaptability and efficiency. Furthermore, we refine the scanning strategy with Mamba by integrating the tensor mode-k unfolding into the Mamba network. This approach emphasizes the low-rank properties of tensors along various modes, while conveniently facilitating 12 scanning directions. Numerical and visual comparisons on both simulation and real datasets demonstrate the superiority of our proposed MiJUN, and achieving overwhelming detail representation.

Image dehazing is a crucial task that involves the enhancement of degraded images to recover their sharpness and textures. While vision Transformers have exhibited impressive results in diverse dehazing tasks, their quadratic complexity and lack of dehazing priors pose significant drawbacks for real-world applications. In this paper, guided by triple priors, Bright Channel Prior (BCP), Dark Channel Prior (DCP), and Histogram Equalization (HE), we propose a Prior-guided Hierarchical Harmonization Network (PGHHNet) for image dehazing. PGHNet is built upon the UNet-like architecture with an efficient encoder and decoder, consisting of two module types: (1) Prior aggregation module that injects BCP/DCP and selects diverse contexts with gating attention. (2) Feature harmonization modules that subtract low-frequency components from spatial and channel aspects and learn more informative feature distributions to equalize the feature maps. Inspired by observing the sparsity of BCP/DCP and the histogram equalization, we harmonize the deep features using a histogram equation-guided module and further leverage BCP/DCP to guide spatial attention through a sandwich module as the bottleneck. Comprehensive experiments demonstrate that our model efficiently attains the highest level of performance among existing methods across four different datasets for image dehazing tasks.

The domain of non-line-of-sight (NLOS) imaging is advancing rapidly, offering the capability to reveal occluded scenes that are not directly visible. However, contemporary NLOS systems face several significant challenges: (1) The computational and storage requirements are profound due to the inherent three-dimensional grid data structure, which restricts practical application. (2) The simultaneous reconstruction of albedo and depth information requires a delicate balance using hyperparameters in the loss function, rendering the concurrent reconstruction of texture and depth information difficult. This paper introduces the innovative methodology, DG-NLOS, which integrates an albedo-focused reconstruction branch dedicated to albedo information recovery and a depth-focused reconstruction branch that extracts geometrical structure, to overcome these obstacles. The dual-branch framework segregates content delivery to the respective reconstructions, thereby enhancing the quality of the retrieved data. To our knowledge, we are the first to employ the GNN as a fundamental component to transform dense NLOS grid data into sparse structural features for efficient reconstruction. Comprehensive experiments demonstrate that our method attains the highest level of performance among existing methods across synthetic and real data.

Although significant progress has been made in enhancing visibility, retrieving texture details, and mitigating noise in Low-Light (LL) images, the challenge persists in applying current Low-Light Image Enhancement (LLIE) methods to real-world scenarios, primarily due to the diverse illumination conditions encountered. Furthermore, the quest for generating enhancements that are visually realistic and attractive remains an underexplored realm. In response to these challenges, we present a novel LLIE framework with the guidance of Generative Perceptual Priors (GPP-LLIE) derived from vision-language models (VLMs). Specifically, we first propose a pipeline that guides VLMs to assess multiple visual attributes of the LL image and quantify the assessment to output the global and local perceptual priors. Subsequently, to incorporate these generative perceptual priors to benefit LLIE, we introduce a transformer-based backbone in the diffusion process, and develop a new layer normalization (GPP-LN) and an attention mechanism (LPP-Attn) guided by global and local perceptual priors. Extensive experiments demonstrate that our model outperforms current SOTA methods on paired LL datasets and exhibits superior generalization on real-world data.

Diffusion models have demonstrated impressive performance in face restoration. Yet, their multi-step inference process remains computationally intensive, limiting their applicability in real-world scenarios. Moreover, existing methods often struggle to generate face images that are harmonious, realistic, and consistent with the subject’s identity. In this work, we propose OSDFace, a novel one-step diffusion model for face restoration. Specifically, we propose a visual representation embedder (VRE) to better capture prior information and understand the input face. In VRE, low-quality faces are processed by a visual tokenizer and subsequently embedded with a vector-quantized dictionary to generate visual prompts. Additionally, we incorporate a facial identity loss derived from face recognition to further ensure identity consistency. We further employ a generative adversarial network (GAN) as a guidance model to encourage distribution alignment between the restored face and the ground truth. Experimental results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics, generating high-fidelity, natural face images with high identity consistency. The code and model will be released at https://github.com/jkwang28/OSDFace.

The Mamba-based image restoration backbones have recently demonstrated significant potential in balancing global reception and computational efficiency. However, the inherent causal modeling limitation of Mamba, where each token depends solely on its predecessors in the scanned sequence, restricts the full utilization of pixels across the image and thus presents new challenges in image restoration. In this work, we propose MambaIRv2, which equips Mamba with the non-causal modeling ability similar to ViTs to reach the attentive state space restoration model. Specifically, the proposed attentive state-space equation allows to attend beyond the scanned sequence and facilitate image unfolding with just one single scan. Moreover, we further introduce a semantic-guided neighboring mechanism to encourage interaction between distant but similar pixels. Extensive experiments show our MambaIRv2 outperforms SRFormer by even 0.35dB PSNR for lightweight SR even with 9.3% less parameters and suppresses HAT on classic SR by up to 0.29dB. Code is available at https://github.com/csguoh/MambaIR.

While deep neural networks have revolutionized image de-noising capabilities, their deployment on edge devices remains challenging due to substantial computational and memory requirements. To this end, we present DnLUT, an ultra-efficient lookup table-based framework that achieves high-quality color image denoising with minimal resource consumption. Our key innovation lies in two complementary components: a Pairwise Channel Mixer (PCM) that effectively captures inter-channel correlations and spatial dependencies in parallel, and a novel L-shaped convolution design that maximizes receptive field coverage while minimizing storage overhead. By converting these components into optimized lookup tables post-training, DnLUT achieves remarkable efficiency - requiring only 500KB storage and 0.1% energy consumption compared to its CNN contestant DnCNN, while delivering 20× faster inference. Extensive experiments demonstrate that DnLUT outperforms all existing LUT-based methods by over 1dB in PSNR, establishing a new state-of-the-art in resource-efficient color image de-noising. The project is available at https://github.com/Stephen0808/DnLUT.

Recent advancements in all-in-one image restoration models have revolutionized the ability to address diverse degradations through a unified framework. However, parameters tied to specific tasks often remain inactive for other tasks, making mixture-of-experts (MoE) architectures a natural extension. Despite this, MoEs often show inconsistent behavior, with some experts unexpectedly generalizing across tasks while others struggle within their intended scope. This hinders leveraging MoEs’ computational benefits by bypassing irrelevant experts during inference. We attribute this undesired behavior to the uniform and rigid architecture of traditional MoEs. To address this, we introduce “complexity experts” – flexible expert blocks with varying computational complexity and receptive fields. A key challenge is assigning tasks to each expert, as degradation complexity is unknown in advance. Thus, we execute tasks with a simple bias toward lower complexity. To our surprise, this preference effectively drives task-specific allocation, assigning tasks to experts with the appropriate complexity. Extensive experiments validate our approach, demonstrating the ability to bypass irrelevant experts during inference while maintaining superior performance. The proposed MoCE-IR model outperforms state-of-the-art methods, affirming its efficiency and practical applicability. The source code and models are publicly available at eduardzamfir.github.io/MoCE-IR/

Diffusion-Based image super-resolution (SR) models have shown superior performance at the cost of multiple denoising steps. However, even though the denoising step has been reduced to one, they require high computational costs and storage requirements, making it difficult for deployment on hardware devices. To address these issues, we propose a novel post-training quantization approach with adaptive scale in one-step diffusion (OSD) image SR, PassionSR. First, we simplify OSD model to two core components, UNet and Variational Autoencoder (VAE) by removing the CLIPEncoder. Secondly, we propose Learnable Boundary Quantizer (LBQ) and Learnable Equivalent Transformation (LET) to optimize the quantization process and manipulate activation distributions for better quantization. Finally, we design a Distributed Quantization Calibration (DQC) strategy that stabilizes the training of quantized parameters for rapid convergence. Comprehensive experiments demonstrate that PassionSR with 8-bit and 6-bit obtains comparable visual results with full-precision model. Moreover, PassionSR achieves significant advantages over recent leading low-bit quantization SR methods. Code will be at https://github.com/libozhu03/PassionSR.

Reasoning capability plays a significantly critical role in the the broad applications of Large Language Models (LLMs).To enhance the reasoning performance of LLMs, diverse Reinforcement Learning (RL)-based fine-tuning approaches have been proposed to address the limited generalization capability of LLMs trained solely via Supervised Fine-Tuning (SFT).Despite their effectiveness, two major limitations hinder the advancement of LLMs.First, vanilla RL-based approaches ignore annotated Chainof-Thought (CoT) and incorporate unstable reasoning path sampling, which typically results in model collapse, unstable training process, and suboptimal performance.Second, existing SFT approaches generally overemphasize the annotated CoT, potentially leading to performance degradation due to insufficient exploitation of potential CoT.In this paper, we propose a Contrastive learning with annotated CoT-based Reinforced Fine-Tuning approach, i.e., CARFT, to enhance the reasoning performance of LLMs while addressing the aforementioned limitations.Specifically, we propose learning a representation for each CoT.Based on this representation, we design novel contrastive signals to guide the fine-tuning process.Our approach not only fully exploits the available annotated CoT but also stabilizes the finetuning procedure by incorporating an additional unsupervised learning signal.We conduct comprehensive experiments and in-depth analysis with three baseline approaches, two foundation models, and two datasets to demonstrate significant advantages of CARFT in terms of robustness, performance (up to 10.15%), and efficiency (up to 30.62%).Code is available at https://github.com/WNQzhu/CARFT.

Diffusion models have demonstrated remarkable success in image restoration tasks. However, their multi-step denoising process introduces significant computational overhead, limiting their practical deployment. Furthermore, existing methods struggle to effectively remove severe JPEG artifact, especially in highly compressed images. To address these challenges, we propose CODiff, a compression-aware one-step diffusion model for JPEG artifact removal. The core of CODiff is the compression-aware visual embedder (CaVE), which extracts and leverages JPEG compression priors to guide the diffusion model. We propose a dual learning strategy that combines explicit and implicit learning. Specifically, explicit learning enforces a quality prediction objective to differentiate low-quality images with different compression levels. Implicit learning employs a reconstruction objective that enhances the model's generalization. This dual learning allows for a deeper and more comprehensive understanding of JPEG compression. Experimental results demonstrate that CODiff surpasses recent leading methods in both quantitative and visual quality metrics. The code is released at https://github.com/jp-guo/CODiff.

We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent complexity of articulated human poses and the scarcity of high-quality whole-body pose datasets. To address these limitations, we introduce a Diffusion model as body Pose prior (DPoser) and extend it to DPoser-X for expressive whole-body human pose modeling. Our approach unifies various pose-centric tasks as inverse problems, solving them through variational diffusion sampling. To enhance performance on downstream applications, we introduce a novel truncated timestep scheduling method specifically designed for pose data characteristics. We also propose a masked training mechanism that effectively combines whole-body and part-specific datasets, enabling our model to capture interdependencies between body parts while avoiding overfitting to specific actions. Extensive experiments demonstrate DPoser-X's robustness and versatility across multiple benchmarks for body, hand, face, and full-body pose modeling. Our model consistently outperforms state-of-the-art alternatives, establishing a new benchmark for whole-body human pose prior modeling.

Low-light image enhancement (LLIE) aims to improve the visibility of images captured in poorly lit environments. Prevalent event-based solutions primarily utilize events triggered by motion, i.e., ''motion events'' to strengthen only the edge texture, while leaving the high dynamic range and excellent low-light responsiveness of event cameras largely unexplored. This paper instead opens a new avenue from the perspective of estimating the illumination using ''temporal-mapping'' events, i.e., by converting the timestamps of events triggered by a transmittance modulation into brightness values. The resulting fine-grained illumination cues facilitate a more effective decomposition and enhancement of the reflectance component in low-light images through the proposed Illumination-aided Reflectance Enhancement module. Furthermore, the degradation model of temporal-mapping events under low-light condition is investigated for realistic training data synthesizing. To address the lack of datasets under this regime, we construct a beam-splitter setup and collect EvLowLight dataset that includes images, temporal-mapping events, and motion events. Extensive experiments across 5 synthetic datasets and our real-world EvLowLight dataset substantiate that the devised pipeline, dubbed RetinEV, excels in producing well-illuminated, high dynamic range images, outperforming previous state-of-the-art event-based methods by up to 6.62 dB, while maintaining an efficient inference speed of 35.6 frame-per-second on a 640X480 image.

Knowledge distillation aims to transfer knowledge from a large teacher model to a compact student counterpart, often coming with a significant performance gap between them. Interestingly, we find that a too-large performance gap can hamper the training process. To alleviate this, we propose a **Gap Preserving Distillation (GPD)** method that trains an additional dynamic teacher model from scratch along with the student to maintain a reasonable performance gap. To further strengthen distillation, we develop a hard strategy by enforcing both models to share parameters. Besides, we also build the soft bidirectional mappings between them through ***Inverse Reparameterization (IR)*** and ***Channel-Branch Reparameterization (CBR)***. IR initializes a larger dynamic teacher with approximately the same accuracy as the student to avoid a too large gap in early stage of training. CBR enables direct extraction of an effective student model from the dynamic teacher without post-training. In experiments, GPD significantly outperforms existing distillation methods on top of both CNNs and transformers, achieving up to 1.58\% accuracy improvement. Interestingly, GPD also generalizes well to the scenarios without a pre-trained teacher, including training from scratch and fine-tuning, yielding a large improvement of 1.80\% and 0.89\% on ResNet18, respectively.

Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion-based models (DM) have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution. To tackle these problems, we propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task. Specifically, Reti-Diff comprises two significant components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RGformer). RLDM is designed to acquire Retinex knowledge, extracting reflectance and illumination priors to facilitate detailed reconstruction and illumination correction. RGformer subsequently utilizes these compact priors to guide the decomposition of image features into their respective reflectance and illumination components. Following this, RGformer further enhances and consolidates these decomposed features, resulting in the production of refined images with consistent content and robustness to handle complex degradation scenarios. Extensive experiments demonstrate that Reti-Diff outperforms existing methods on three IDIR tasks, as well as downstream applications.

We propose a generative agent that augments training datasets with synthetic data for model fine-tuning. Unlike prior work, which uniformly samples synthetic data, our agent iteratively generates relevant samples on-the-fly, aligning with the target distribution. It prioritizes synthetic data that complements difficult training samples, focusing on those with high variance in gradient updates. Experiments across several image classification tasks demonstrate the effectiveness of our approach.

Large Language Models (LLMs) have greatly pushed forward advancements in natural language processing, yet their high memory and computational demands hinder practical deployment. Binarization, as an effective compression technique, can shrink model weights to just 1 bit, significantly reducing the high demands on computation and memory. However, current binarization methods struggle to narrow the distribution gap between binarized and full-precision weights, while also overlooking the column deviation in LLM weight distribution. To tackle these issues, we propose ARB-LLM, a novel 1-bit post-training quantization (PTQ) technique tailored for LLMs. To narrow the distribution shift between binarized and full-precision weights, we first design an alternating refined binarization (ARB) algorithm to progressively update the binarization parameters, which significantly reduces the quantization error. Moreover, considering the pivot role of calibration data and the column deviation in LLM weights, we further extend ARB to ARB-X and ARB-RC. In addition, we refine the weight partition strategy with column-group bitmap (CGB), which further enhance performance. Equipping ARB-X and ARB-RC with CGB, we obtain ARB-LLM$_{\text{X}}$ and ARB-LLM$ _{\text{RC}} $ respectively, which significantly outperform state-of-the-art (SOTA) binarization methods for LLMs. As a binary PTQ method, our ARB-LLM$ _{\text{RC}} $ is the first to surpass FP16 models of the same size. Code: https://github.com/ZHITENGLI/ARB-LLM.

We introduce a novel Multi-modal Guided Real-World Face Restoration (MGFR) technique designed to improve the quality of facial image restoration from low-quality inputs. Leveraging a blend of attribute text prompts, high-quality reference images, and identity information, MGFR can mitigate the generation of false facial attributes and identities often associated with generative face restoration methods. By incorporating a dual-control adapter and a two-stage training strategy, our method effectively utilizes multi-modal prior information for targeted restoration tasks. We also present the Reface-HQ dataset, comprising over 21,000 high-resolution facial images across 4800 identities, to address the need for reference face training images. Our approach achieves superior visual quality in restoring facial details under severe degradation and allows for controlled restoration processes, enhancing the accuracy of identity preservation and attribute correction. Including negative quality samples and attribute prompts in the training further refines the model's ability to generate detailed and perceptually accurate images.

While super-resolution (SR) methods based on diffusion models (DM) have demonstrated inspiring performance, their deployment is impeded due to the heavy request of memory and computation. Recent researchers apply two kinds of methods to compress or fasten the DM. One is to compress the DM into 1-bit, aka binarization, alleviating the storage and computation pressure. The other distills the multi-step DM into only one step, significantly speeding up inference process. Nonetheless, it remains impossible to deploy DM to resource-limited edge devices. To address this problem, we propose BiMaCoSR, which combines binarization and one-step distillation to obtain extreme compression and acceleration. To prevent the catastrophic collapse of the model caused by binarization, we proposed sparse matrix branch (SMB) and low rank matrix branch (LRM). Both auxiliary branches pass the full-precision (FP) information but in different ways. SMB absorbs the extreme values and its output is high rank, carrying abundant FP information. Whereas, the design of LRMB is inspired by LoRA and is initialized with the top r SVD components, outputting low rank representation. The computation and storage overhead of our proposed branches can be safely ignored. Comprehensive comparison experiments are conducted to exhibit BiMaCoSR outperforms current state-of-the-art binarization methods and gains competitive performance compared with FP one-step model. Moreover, we achieve excellent compression and acceleration. BiMaCoSR achieves a 23.8x compression ratio and a 27.4x speedup ratio compared to FP counterpart. Our code and model are available at https://github.com/Kai-Liu001/BiMaCoSR

Human body restoration, as a specific application of image restoration, is widely applied in practice and plays a vital role across diverse fields. However, thorough research remains difficult, particularly due to the lack of benchmark datasets. In this study, we propose a high-quality dataset automated cropping and filtering (HQ-ACF) pipeline. This pipeline leverages existing object detection datasets and other unlabeled images to automatically crop and filter high-quality human images. Using this pipeline, we constructed a person-based restoration with sophisticated objects and natural activities (PERSONA) dataset, which includes training, validation, and test sets. The dataset significantly surpasses other human-related datasets in both quality and content richness. Finally, we propose OSDHuman, a novel one-step diffusion model for human body restoration. Specifically, we propose a high-fidelity image embedder (HFIE) as the prompt generator to better guide the model with low-quality human image information, effectively avoiding misleading prompts. Experimental results show that OSDHuman outperforms existing methods in both visual quality and quantitative metrics. The dataset and code are available at: https://github.com/gobunu/OSDHuman.

Concealed object segmentation (COS) is a challenging problem that focuses on identifying objects that are visually blended into their background. Existing methods often employ reversible strategies to concentrate on uncertain regions but only focus on the mask level, overlooking the valuable of the RGB domain. To address this, we propose a Reversible Unfolding Network (RUN) in this paper. RUN formulates the COS task as a foreground-background separation process and incorporates an extra residual sparsity constraint to minimize segmentation uncertainties. The optimization solution of the proposed model is unfolded into a multistage network, allowing the original fixed parameters to become learnable. Each stage of RUN consists of two reversible modules: the Segmentation-Oriented Foreground Separation (SOFS) module and the Reconstruction-Oriented Background Extraction (ROBE) module. SOFS applies the reversible strategy at the mask level and introduces Reversible State Space to capture non-local information. ROBE extends this to the RGB domain, employing a reconstruction network to address conflicting foreground and background regions identified as distortion-prone areas, which arise from their separate estimation by independent modules. As the stages progress, RUN gradually facilitates reversible modeling of foreground and background in both the mask and RGB domains, reducing false-positive and false-negative regions. Extensive experiments demonstrate the superior performance of RUN and underscore the promise of unfolding-based frameworks for COS and other high-level vision tasks. Code is available at https://github.com/ChunmingHe/RUN.

Diffusion models (DMs) have significantly advanced the development of real-world image super-resolution (Real-ISR), but the computational cost of multi-step diffusion models limits their application. One-step diffusion models generate high-quality images in a one sampling step, greatly reducing computational overhead and inference latency. However, most existing one-step diffusion methods are constrained by the performance of the teacher model, where poor teacher performance results in image artifacts. To address this limitation, we propose FluxSR, a novel one-step diffusion Real-ISR technique based on flow matching models. We use the state-of-the-art diffusion model FLUX.1-dev as both the teacher model and the base model. First, we introduce Flow Trajectory Distillation (FTD) to distill a multi-step flow matching model into a one-step Real-ISR. Second, to improve image realism and address high-frequency artifact issues in generated images, we propose TV-LPIPS as a perceptual loss and introduce Attention Diversification Loss (ADL) as a regularization term to reduce token similarity in transformer, thereby eliminating high-frequency artifacts. Comprehensive experiments demonstrate that our method outperforms existing one-step diffusion-based Real-ISR methods. The code and model will be released at \url{https://github.com/JianzeLi-114/FluxSR}.

Existing feedforward subject-driven video customization methods mainly study single-subject scenarios due to the difficulty of constructing multi-subject training data pairs. Another challenging problem that how to use the signals such as depth, mask, camera, and text prompts to control and edit the subject in the customized video is still less explored. In this paper, we first propose a data construction pipeline, VideoCus-Factory, to produce training data pairs for multi-subject customization from raw videos without labels and control signals such as depth-to-video and mask-to-video pairs. Based on our constructed data, we develop an Image-Video Transfer Mixed (IVTM) training with image editing data to enable instructive editing for the subject in the customized video. Then we propose a diffusion Transformer framework, OmniVCus, with two embedding mechanisms, Lottery Embedding (LE) and Temporally Aligned Embedding (TAE). LE enables inference with more subjects by using the training subjects to activate more frame embeddings. TAE encourages the generation process to extract guidance from temporally aligned control signals by assigning the same frame embeddings to the control and noise tokens. Experiments demonstrate that our method significantly surpasses state-of-the-art methods in both quantitative and qualitative evaluations. Project page is at https://caiyuanhao1998.github.io/project/OmniVCus/

Diffusion models have demonstrated promising performance in real-world video super-resolution (VSR). However, the dozens of sampling steps they require, make inference extremely slow. Sampling acceleration techniques, particularly single-step, provide a potential solution. Nonetheless, achieving one step in VSR remains challenging, due to the high training overhead on video data and stringent fidelity demands. To tackle the above issues, we propose DOVE, an efficient one-step diffusion model for real-world VSR. DOVE is obtained by fine-tuning a pretrained video diffusion model (*i.e.*, CogVideoX). To effectively train DOVE, we introduce the latent-pixel training strategy. The strategy employs a two-stage scheme to gradually adapt the model to the video super-resolution task. Meanwhile, we design a video processing pipeline to construct a high-quality dataset tailored for VSR, termed HQ-VSR. Fine-tuning on this dataset further enhances the restoration capability of DOVE. Extensive experiments show that DOVE exhibits comparable or superior performance to multi-step diffusion-based VSR methods. It also offers outstanding inference efficiency, achieving up to a **28$\times$** speed-up over existing methods such as MGLD-VSR. Code is available at: https://github.com/zhengchen1999/DOVE.

Multi-frame video enhancement tasks aim to improve the spatial and temporal resolution and quality of video sequences by leveraging temporal information from multiple frames, which are widely used in streaming video processing, surveillance, and generation. Although numerous Transformer-based enhancement methods have achieved impressive performance, their computational and memory demands hinder deployment on edge devices. Quantization offers a practical solution by reducing the bit-width of weights and activations to improve efficiency. However, directly applying existing quantization methods to video enhancement tasks often leads to significant performance degradation and loss of fine details. This stems from two limitations: (a) inability to allocate varying representational capacity across frames, which results in suboptimal dynamic range adaptation; (b) over-reliance on full-precision teachers, which limits the learning of low-bit student models. To tackle these challenges, we propose a novel quantization method for video enhancement: Progressive Multi-Frame Quantization for Video Enhancement (PMQ-VE). This framework features a coarse-to-fine two-stage process: Backtracking-based Multi-Frame Quantization (BMFQ) and Progressive Multi-Teacher Distillation (PMTD). BMFQ utilizes a percentile-based initialization and iterative search with pruning and backtracking for robust clipping bounds. PMTD employs a progressive distillation strategy with both full-precision and multiple high-bit (INT) teachers to enhance low-bit models' capacity and quality. Extensive experiments demonstrate that our method outperforms existing approaches, achieving state-of-the-art performance across multiple tasks and benchmarks. The code will be made publicly available.

Human-centered images often suffer from severe generic degradation during transmission and are prone to human motion blur (HMB), making restoration challenging. Existing research lacks sufficient focus on these issues, as both problems often coexist in practice. To address this, we design a degradation pipeline that simulates the coexistence of HMB and generic noise, generating synthetic degraded data to train our proposed HAODiff, a human-aware one-step diffusion. Specifically, we propose a triple-branch dual-prompt guidance (DPG), which leverages high-quality images, residual noise (LQ minus HQ), and HMB segmentation masks as training targets. It produces a positive–negative prompt pair for classifier‑free guidance (CFG) in a single diffusion step. The resulting adaptive dual prompts let HAODiff exploit CFG more effectively, boosting robustness against diverse degradations. For fair evaluation, we introduce MPII‑Test, a benchmark rich in combined noise and HMB cases. Extensive experiments show that our HAODiff surpasses existing state-of-the-art (SOTA) methods in terms of both quantitative metrics and visual quality on synthetic and real-world datasets, including our introduced MPII-Test. Code is available at: https://github.com/gobunu/HAODiff.

Pretrained latent diffusion models have shown strong potential for lossy image compression, owing to their powerful generative priors. Most existing diffusion-based methods reconstruct images by iteratively denoising from random noise, guided by compressed latent representations. While these approaches have achieved high reconstruction quality, their multi-step sampling process incurs substantial computational overhead. Moreover, they typically require training separate models for different compression bit-rates, leading to significant training and storage costs. To address these challenges, we propose a one-step diffusion codec across multiple bit-rates. termed OSCAR. Specifically, our method views compressed latents as noisy variants of the original latents, where the level of distortion depends on the bit-rate. This perspective allows them to be modeled as intermediate states along a diffusion trajectory. By establishing a mapping from the compression bit-rate to a pseudo diffusion timestep, we condition a single generative model to support reconstructions at multiple bit-rates. Meanwhile, we argue that the compressed latents retain rich structural information, thereby making one-step denoising feasible. Thus, OSCAR replaces iterative sampling with a single denoising pass, significantly improving inference efficiency. Extensive experiments demonstrate that OSCAR achieves superior performance in both quantitative and visual quality metrics. The code and models are available at https://github.com/jp-guo/OSCAR/.

Diffusion models have demonstrated excellent performance for real-world image super-resolution (Real-ISR), albeit at high computational costs. Most existing methods are trying to derive one-step diffusion models from multi-step counterparts through knowledge distillation (KD) or variational score distillation (VSD). However, these methods are limited by the capabilities of the teacher model, especially if the teacher model itself is not sufficiently strong. To tackle these issues, we propose a new One-Step \textbf{D}iffusion model with a larger-scale \textbf{D}iffusion \textbf{D}iscriminator for SR, called D$^3$SR. Our discriminator is able to distill noisy features from any time step of diffusion models in the latent space. In this way, our diffusion discriminator breaks through the potential limitations imposed by the presence of a teacher model. Additionally, we improve the perceptual loss with edge-aware DISTS (EA-DISTS) to enhance the model's ability to generate fine details. Our experiments demonstrate that, compared with previous diffusion-based methods requiring dozens or even hundreds of steps, our D$^3$SR attains comparable or even superior results in both quantitative metrics and qualitative evaluations. Moreover, compared with other methods, D$^3$SR achieves at least $3\times$ faster inference speed and reduces parameters by at least 30\%.

The real world is dynamic, yet most image fusion methods process static frames independently, ignoring temporal correlations in videos and leading to flickering and temporal inconsistency. To address this, we propose Unified Video Fusion (UniVF), a novel and unified framework for video fusion that leverages multi-frame learning and optical flow-based feature warping for informative, temporally coherent video fusion. To support its development, we also introduce Video Fusion Benchmark (VF-Bench), the first comprehensive benchmark covering four video fusion tasks: multi-exposure, multi-focus, infrared-visible, and medical fusion. VF-Bench provides high-quality, well-aligned video pairs obtained through synthetic data generation and rigorous curation from existing datasets, with a unified evaluation protocol that jointly assesses the spatial quality and temporal consistency of video fusion. Extensive experiments show that UniVF achieves state-of-the-art results across all tasks on VF-Bench. Project page: [vfbench.github.io](https://vfbench.github.io).

Incompletely-Supervised Concealed Object Segmentation (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments, utilizing incompletely annotated data, such as weak and semi-annotations, for model training. This task remains highly challenging due to (1) the limited supervision provided by the incompletely annotated training data, and (2) the difficulty of distinguishing concealed objects from the background, which arises from the intrinsic similarities in concealed scenarios. In this paper, we introduce the first unified method for ISCOS to address these challenges. To tackle the issue of incomplete supervision, we propose a unified mean-teacher framework, SEE, that leverages the vision foundation model, "Segment Anything Model (SAM)", to generate pseudo-labels using coarse masks produced by the teacher model as prompts. To mitigate the effect of low-quality segmentation masks, we introduce a series of strategies for pseudo-label generation, storage, and supervision. These strategies aim to produce informative pseudo-labels, store the best pseudo-labels generated, and select the most reliable components to guide the student model, thereby ensuring robust network training. Additionally, to tackle the issue of intrinsic similarity, we design a hybrid-granularity feature grouping module that groups features at different granularities and aggregates these results. By clustering similar features, this module promotes segmentation coherence, facilitating more complete segmentation for both single-object and multiple-object images. We validate the effectiveness of our approach across multiple ISCOS tasks, and experimental results demonstrate that our method achieves state-of-the-art performance. Furthermore, SEE can serve as a plug-and-play solution, enhancing the performance of existing models.

Deep generative models have gained considerable attention in low-level vision tasks due to their powerful generative capabilities. Among these, diffusion model-based approaches, which employ a forward diffusion process to degrade an image and a reverse denoising process for image generation, have become particularly prominent for producing high-quality, diverse samples with intricate texture details. Despite their widespread success in low-level vision, there remains a lack of a comprehensive, insightful survey that synthesizes and organizes the advances in diffusion model-based techniques. To address this gap, this paper presents the first comprehensive review focused on denoising diffusion models applied to low-level vision tasks, covering both theoretical and practical contributions. We outline three general diffusion modeling frameworks and explore their connections with other popular deep generative models, establishing a solid theoretical foundation for subsequent analysis. We then categorize diffusion models used in low-level vision tasks from multiple perspectives, considering both the underlying framework and the target application. Beyond natural image processing, we also summarize diffusion models applied to other low-level vision domains, including medical imaging, remote sensing, and video processing. Additionally, we provide an overview of widely used benchmarks and evaluation metrics in low-level vision tasks. Our review includes an extensive evaluation of diffusion model-based techniques across six representative tasks, with both quantitative and qualitative analysis. Finally, we highlight the limitations of current diffusion models and propose four promising directions for future research. This comprehensive review aims to foster a deeper understanding of the role of denoising diffusion models in low-level vision.

The restoration of hyperspectral image (HSI) plays a pivotal role in subsequent hyperspectral image applications. Despite the remarkable capabilities of deep learning, current HSI restoration methods face challenges in effectively exploring the spatial non-local self-similarity and spectral low-rank property inherently embedded with HSIs. This paper addresses these challenges by introducing a latent diffusion enhanced rectangle Transformer for HSI restoration, tackling the non-local spatial similarity and HSI-specific latent diffusion low-rank property. In order to effectively capture non-local spatial similarity, we propose the multi-shape spatial rectangle self-attention module in both horizontal and vertical directions, enabling the model to utilize informative spatial regions for HSI restoration. Meanwhile, we propose a spectral latent diffusion enhancement module that generates the image-specific latent dictionary based on the content of HSI for low-rank vector extraction and representation. This module utilizes a diffusion model to generatively obtain representations of global low-rank vectors, thereby aligning more closely with the desired HSI. A series of comprehensive experiments were carried out on four common hyperspectral image restoration tasks, including HSI denoising, HSI super-resolution, HSI reconstruction, and HSI inpainting. The results of these experiments highlight the effectiveness of our proposed method, as demonstrated by improvements in both objective metrics and subjective visual quality.

Deep neural networks for real-time video matting suffer significant computational limitations on edge devices, hindering their adoption in widespread applications such as online conferences and short-form video production. Binarization emerges as one of the most common neural network compression approaches, substantially curbing computational and memory requirements through compact 1-bit parameters and efficient bitwise operations. However, the empirical observation reveals that accuracy and efficiency limitations exist in the binarized video matting network due to its degenerated encoder and redundant decoder. Following a theoretical analysis based on the information bottleneck principle, the limitations are mainly caused by the degradation of prediction-relevant information in the intermediate features and the redundant computation in prediction-irrelevant areas. We presentBiVM, an accurate and resource-efficientBinarized neural network forVideoMatting, where architecture and optimization allow real-time video matting to proceed on edge hardware. First, we present a series of binarized computation structures with elastic shortcuts and evolvable topologies, enabling the constructed encoder backbone to extract high-quality representation from input videos for accurate prediction. Second, we sparse the intermediate feature of the binarized decoder by masking homogeneous parts, allowing the decoder to focus on representation with diverse details while alleviating the computation burden for efficient inference. Furthermore, we construct a localized binarization-aware mimicking framework with the information-guided strategy, prompting matting-related representation in full-precision counterparts to be accurately and fully utilized. Comprehensive experiments show that the proposed BiVM surpasses alternative binarized video matting networks, including state-of-the-art (SOTA) binarization methods, by a substantial margin. For example, BiVM surpasses 16.67 MAD compared to SOTA binarization on the VM dataset. Notably, our approach can even perform comparably to the full-precision counterpart in terms of visual quality. Moreover, our BiVM achieves significant savings of 14.3× and 21.6× in computation and storage costs, respectively. We also evaluate BiVM on ARM CPU hardware, underscoring its potential for deployment in resource-constrained scenarios.

Snapshot compressive imaging (SCI) surges as a novel way of capturing hyperspectral images. It operates an optical encoder to compress the 3D data into a 2D measurement and adopts a software decoder for the signal reconstruction. Recently, a representative SCI set-up of coded aperture snapshot compressive imager (CASSI) with Transformer reconstruction backend remarks high-fidelity sensing performance. However, dominant spatial and spectral attention designs show limitations in hyperspectral modeling. The spatial attention values describe the inter-pixel correlation but overlook the across-spectra variation within each pixel. The spectral attention size is unscalable to the token spatial size and thus bottlenecks information allocation. Besides, CASSI entangles the spatial and spectral information into a 2D measurement, placing a barrier for information disentanglement and modeling. In addition, CASSI blocks the light with a physical binary mask, yielding the masked data loss. To tackle above challenges, we propose a spatial-spectral ($S^{2}$S2-) Transformer implemented by a paralleled attention design and a mask-aware learning strategy. First, we systematically explore pros and cons of different spatial (-spectral) attention designs, based on which we find performing both attentions in parallel well disentangles and models the blended information. Second, the masked pixels induce higher prediction difficulty and should be treated differently from unmasked ones. We adaptively prioritize the loss penalty attributing to the mask structure by referring to the mask-encoded prediction as an uncertainty estimator. We theoretically discuss the distinct convergence tendencies between masked/unmasked regions of the proposed learning strategy. Extensive experiments demonstrate that on average, the results of the proposed method are superior over the state-of-the-art methods. We empirically visualize and reason the behaviour of spatial and spectral attentions, and comprehensively examine the impact of the mask-aware learning, both of which advances the physics-driven deep network design for the reconstruction with CASSI.

The Diffusion Model (DM) has emerged as the SOTA approach for image synthesis. However, the existing DM cannot perform well on some image-to-image translation (I2I) tasks. Different from image synthesis, some I2I tasks, such as super-resolution, require generating results in accordance with GT images. Traditional DMs for image synthesis require extensive iterations and large denoising models to estimate entire images, which gives their strong generative ability but also leads to artifacts and inefficiency for I2I. To tackle this challenge, we propose a simple, efficient, and powerful DM framework for I2I, called DiffI2I. Specifically, DiffI2I comprises three key components: a compact I2I prior extraction network (CPEN), a dynamic I2I transformer (DI2Iformer), and a denoising network. We train DiffI2I in two stages: pretraining and DM training. For pretraining, GT and input images are fed into CPEN to capture a compact I2I prior representation (IPR) guiding DI2Iformer. In the second stage, the DM is trained to only use the input images to estimate the same IRP as CPEN. Compared to traditional DMs, the compact IPR enables DiffI2I to obtain more accurate outcomes and employ a lighter denoising network and fewer iterations. Through extensive experiments on various I2I tasks, we demonstrate that DiffI2I achieves SOTA performance while significantly reducing computational burdens.

Image denoising has progressed significantly due to the development of effective deep denoisers. To improve the performance in real-world scenarios, recent trends prefer to formulate superior noise models to generate realistic training data, or estimate noise levels to steer non-blind denoisers. In this paper, we bridge both strategies by presenting an innovative noise estimation and realistic noise synthesis pipeline. Specifically, we integrates a fine-grained statistical noise model and contrastive learning strategy, with a unique data augmentation to enhance learning ability. Then, we use this model to estimate noise parameters on evaluation dataset, which are subsequently used to craft camera-specific noise distribution and synthesize realistic noise. One distinguishing feature of our methodology is its adaptability: our pre-trained model can directly estimate unknown cameras, making it possible to unfamiliar sensor noise modeling using only testing images, without calibration frames or paired training data. Another highlight is our attempt in estimating parameters for fine-grained noise models, which extends the applicability to even more challenging low-light conditions. Through empirical testing, our calibration-free pipeline demonstrates effectiveness in both normal and low-light scenarios, further solidifying its utility in real-world noise synthesis and denoising tasks.

Despite Transformers have achieved significant success in low-level vision tasks, they are constrained by computing self-attention with a quadratic complexity and limited-size windows. This limitation results in a lack of global receptive field across the entire image. Recently, State Space Models (SSMs) have gained widespread attention due to their global receptive field and linear complexity with respect to input length. However, integrating SSMs into low-level vision tasks presents two major challenges: 1) Relationship degradation of long-range tokens with a long-range forgetting problem by encoding pixel-by-pixel high-resolution images. 2) Significant redundancy in the existing multi-direction scanning strategy. To this end, we propose Hi-Mamba for image super-resolution (SR) to address these challenges, which unfolds the image with only a single scan. Specifically, the Global Hierarchical Mamba Block (GHMB) enables token interactions across the entire image, providing a global receptive field while leveraging a multi-scale structure to facilitate long-range dependency learning. Additionally, the Direction Alternation Module (DAM) adjusts the scanning patterns of GHMB across different layers to enhance spatial relationship modeling. Extensive experiments demonstrate that our Hi-Mamba achieves 0.2-0.27dB PSNR gains on the Urban100 dataset across different scaling factors compared to the state-of-the-art MambaIRv2 for SR. Moreover, our lightweight Hi-Mamba also outperforms lightweight SRFormer by 0.39dB PSNR for $\times 2$ SR.

Currently, two main research lines in efficient context modeling for image dehazing are tailoring effective feature modulation mechanisms and utilizing the Fourier transform more precisely. The former is usually based on self-scale features that ignore complementary cross-scale/level features, and the latter tends to overlook regions with pronounced haze degradation and intricate structures. This paper introduces a novel spatial and frequency modulation perspective to synergistically investigate contextual feature modeling for efficient image dehazing. Specifically, we delicately develop a Spatial Frequency Modulator (SFM) equipped with a Cross-Scale Modulator (CSM) and Frequency Modulator (FM) to implement intra-block feature modulation. The CSM progressively aggregates hierarchical features across different scales, employing them for spatial self-modulation, and the FM subsequently adopts a dual-branch design to focus more on the crucial areas with severe haze and complex structures for reconstruction. Further, we propose a Cross-Level Modulator (CLM) to facilitate inter-block feature mutual modulation, enhancing seamless interaction between features at different depths and layers. Integrating the above-developed modules into the U-Net architecture, we construct a two-stage spatial frequency modulation network (SFMN). Extensive quantitative and qualitative evaluations showcase the superior performance and efficiency of the proposed SFMN over recent state-of-the-art image dehazing methods. The source code can be found in https://github.com/it-hao/SFMN.

Taking photographs through windows is an inevitable scenario in the real world, but glass windows are not ideally clean in most cases. Although there exists various raindrop removal methods, the occlusion of dirt, as another dirty window case, has not been well valued. The vital reasons include i) the limitation of the optical imaging model proposed in previous methods, and ii) the shortage of a practical dataset for sufficient types of dirty glass windows. To fill this research gap, in this paper, we first propose a general optical imaging model that fits widely used dirty window cases. Following this, training and testing synthetic datasets are generated, and real-world dirty window data are collected to evaluate the effectiveness of our imaging model and synthetic data. For the methodology part, we propose an optics-guided Transformer network to solve this special image restoration problem, i.e., the dirt removal for images taken through a dirty window. Experimental results demonstrate that our imaging model is effective and robust. Our proposed network leads to higher performance than existing methods on both synthetic and real-world dirty window images. Code and data are available at https://github.com/Zongliang-Wu/ReDNet.

A fundamental task in the realms of computer vision, Low-Rank Matrix Recovery (LRMR) focuses on the inherent low-rank structure precise recovery from incomplete data and/or corrupted measurements given that the rank is a known prior or accurately estimated. However, it remains challenging for existing rank estimation methods to accurately estimate the rank of an ill-conditioned matrix. Also, existing LRMR optimization methods are heavily dependent on the chosen parameters, and are therefore difficult to adapt to different situations. Addressing these issues, A novel LEarning-based low-rank matrix recovery with Rank Estimation (LERE) is proposed. More specifically, considering the characteristics of the Gerschgorin disk's center and radius, a new heuristic decision rule in the Gerschgorin Disk Theorem is significantly enhanced and the low-rank boundary can be exactly located, which leads to a marked improvement in the accuracy of rank estimation. According to the estimated rank, we select row and column sub-matrices from the observation matrix by uniformly random sampling. A 17-iteration feedforward-recurrent-mixed neural network is then adapted to learn the parameters in the sub-matrix recovery processing. Finally, by the correlation of the row sub-matrix and column sub-matrix, LERE successfully recovers the underlying low-rank matrix. Overall, LERE is more efficient and robust than existing LRMR methods. Experimental results demonstrate that LERE surpasses state-of-the-art (SOTA) methods. The code for this work is accessible at https://github.com/zhengqinxu/LERE.

Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Due to the inherent property of diffusion models, most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. Moreover, such long sampling chains hinder understanding the relationship between inputs and restoration results since it is hard to compute the gra-dients in the whole chains. In this work, we aim to rethink the diffusion model-based IR models through a different per-spective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR. Specifically, we derive an analytical solution by modeling the entire sampling chain in these IR models as a joint multivariate fixed point system. Based on the analyti-cal solution, we can conduct parallel sampling and restore HQ images without training. Furthermore, we compute fast gradients via DEQ inversion and found that initialization optimization can boost image quality and control the gen-eration direction. Extensive experiments on benchmarks demonstrate the effectiveness of our method on typical IR tasks and real-world settings.

We present Multi-Baseline Radiance Fields (MuRF), a general feed-forward approach to solving sparse view syn-thesis under multiple different baseline settings (small and large baselines, and different number of input views). To render a target novel view, we discretize the 3D space into planes parallel to the target image plane, and accordingly construct a target view frustum volume. Such a target volume representation is spatially aligned with the target view, which effectively aggregates relevant information from the input views for high-quality rendering. It also facilitates subsequent radiance field regression with a convolutional network thanks to its axis-aligned nature. The 3D context modeled by the convolutional network enables our method to synthesis sharper scene structures than prior works. Our MuRF achieves state-of-the-art performance across multiple different baseline settings and diverse scenarios ranging from simple objects (DTU) to complex indoor and outdoor scenes (RealEstatel0K and LLFF). We also show promising zero-shot generalization abilities on the Mip-NeRF 360 dataset, demonstrating the general applicability of MuRF.

Real-world vision tasks frequently suffer from the appearance of unexpected adverse weather conditions, including rain, haze, snow, and raindrops. In the last decade, convolutional neural networks and vision transformers have yielded outstanding results in single-weather video removal. However, due to the absence of appropriate adaptation, most of them fail to generalize to other weather conditions. Although ViWS-Net is proposed to remove ad-verse weather conditions in videos with a single set of pre-trained weights, it is seriously blinded by seen weather at train-time and degenerates when coming to unseen weather during test-time. In this work, we introduce test-time adaptation into adverse weather removal in videos, and propose the first framework that integrates test-time adaptation into the iterative diffusion reverse process. Specifically, we devise a diffusion-based network with a novel temporal noise model to efficiently explore frame-correlated information in degraded video clips at training stage. During inference stage, we introduce a proxy task named Diffusion Tubelet Self-Calibration to learn the primer distribution of test video stream and optimize the model by approx-imating the temporal noise model for online adaptation. Experimental results, on benchmark datasets, demonstrate that our Test-Time Adaptation method with Diffusion-based network(Diff- TTA) outperforms state-of-the-art methods in terms of restoring videos degraded by seen weather conditions. Its generalizable capability is validated with unseen weather conditions in synthesized and real-world videos.

Recently, deep neural networks have achieved excellent performance on low-light raw video enhancement. How-ever, they often come with high computational complexity and large memory costs, which hinder their applications on resource-limited devices. In this paper, we explore the feasibility of applying the extremely compact binary neural network (BNN) to low-light raw video enhancement. Nev-ertheless, there are two main issues with binarizing video enhancement models. One is how to fuse the temporal in-formation to improve low-light denoising without complex modules. The other is how to narrow the performance gap between binary convolutions with the full precision ones. To address the first issue, we introduce a spatial-temporal shift operation, which is easy-to-binarize and effective. The temporal shift efficiently aggregates the features of neigh-bor frames and the spatial shift handles the misalignment caused by the large motion in videos. For the second issue, we present a distribution-aware binary convolution, which captures the distribution characteristics of real-valued in-put and incorporates them into plain binary convolutions to alleviate the degradation in performance. Extensive quantitative and qualitative experiments have shown our high-efficiency binarized low-light raw video enhancement method can attain a promising performance. The code is available at https://github.com/ying-fuIBRVE.

Multi-modality image fusion is a technique that combines information from different sensors or modalities, en-abling the fused image to retain complementary features from each modality, such as functional highlights and texture details. However, effective training of such fusion models is challenging due to the scarcity of ground truth fusion data. To tackle this issue, we propose the Equivariant Multi-Modality imAge fusion (EMMA) paradigm for end-to-end self-supervised learning. Our approach is rooted in the prior knowledge that natural imaging responses are equiv-ariant to certain transformations. Consequently, we introduce a novel training paradigm that encompasses a fusion module, a pseudo-sensing module, and an equivariant fusion module. These components enable the net training to follow the principles of the natural sensing-imaging process while satisfying the equivariant imaging prior. Extensive experiments confirm that EMMA yields high-quality fusion results for infraredvisible and medical images, concurrently facilitating downstream multi-modal segmentation and detection tasks. The code is available at https://github.com/Zhaozixiang1228/MMIF-EMMA.

Transformer architectures have exhibited remarkable performance in image super-resolution (SR). Since the quadratic computational complexity of the self-attention (SA) in Transformer, existing methods tend to adopt SA in a local region to reduce overheads. However, the local design restricts the global context exploitation, which is crucial for accurate image reconstruction. In this work, we propose the Recursive Generalization Transformer (RGT) for image SR, which can capture global spatial information and is suitable for high-resolution images. Specifically, we propose the recursive-generalization self-attention (RG-SA). It recursively aggregates input features into representative feature maps, and then utilizes cross-attention to extract global information. Meanwhile, the channel dimensions of attention matrices ($query$, $key$, and $value$) are further scaled to mitigate the redundancy in the channel domain. Furthermore, we combine the RG-SA with local self-attention to enhance the exploitation of the global context, and propose the hybrid adaptive integration (HAI) for module integration. The HAI allows the direct and effective fusion between features at different levels (local or global). Extensive experiments demonstrate that our RGT outperforms recent state-of-the-art methods quantitatively and qualitatively. Code and pre-trained models are available at https://github.com/zhengchen1999/RGT.

Camouflaged object detection (COD) is the challenging task of identifying camouflaged objects visually blended into surroundings. Albeit achieving remarkable success, existing COD detectors still struggle to obtain precise results in some challenging cases. To handle this problem, we draw inspiration from the prey-vs-predator game that leads preys to develop better camouflage and predators to acquire more acute vision systems and develop algorithms from both the prey side and the predator side. On the prey side, we propose an adversarial training framework, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect. Camouflageator trains the generator and detector in an adversarial way such that the enhanced auxiliary generator helps produce a stronger detector. On the predator side, we introduce a novel COD method, called Internal Coherence and Edge Guidance (ICEG), which introduces a camouflaged feature coherence module to excavate the internal coherence of camouflaged objects, striving to obtain more complete segmentation results. Additionally, ICEG proposes a novel edge-guided separated calibration module to remove false predictions to avoid obtaining ambiguous boundaries. Extensive experiments show that ICEG outperforms existing COD detectors and Camouflageator is flexible to improve various COD detectors, including ICEG, which brings state-of-the-art COD performance.

In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation of tokens from different scopes. In detail, we adopt two types of Transformer blocks. The spatial-wise Transformer block performs fine-grained local patches interactions across tokens defined by spatial dimension. The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension. Based on the concurrent network structure, we design two branches to conduct these two interaction fashions. Within each branch, we employ an encoder-decoder architecture to capture multi-scale features. Besides, we propose the Bidirectional Connection Unit (BCU) to couple the learned representations from these two branches while providing enhanced information fusion. The joint designs make our Xformer powerful to conduct global information modeling in both spatial and channel dimensions. Extensive experiments show that Xformer, under the comparable model complexity, achieves state-of-the-art performance on the synthetic and real-world image denoising tasks. We also provide code and models at https://github.com/gladzhang/Xformer.

Reconstructing high-resolution (HR) images from low-resolution (LR) inputs poses a significant challenge in image super-resolution (SR). While recent approaches have demonstrated the efficacy of intricate operations customized for various objectives, the straightforward stacking of these disparate operations can result in a substantial computational burden, hampering their practical utility. In response, we introduce SeemoRe, an efficient SR model employing expert mining. Our approach strategically incorporates experts at different levels, adopting a collaborative methodology. At the macro scale, our experts address rank-wise and spatial-wise informative features, providing a holistic understanding. Subsequently, the model delves into the subtleties of rank choice by leveraging a mixture of low-rank experts. By tapping into experts specialized in distinct key factors crucial for accurate SR, our model excels in uncovering intricate intra-feature details. This collaborative approach is reminiscent of the concept of “see more", allowing our model to achieve an optimal performance with minimal computational costs in efficient settings.

Lightweight image super-resolution (SR) methods have obtained promising results with moderate model complexity. These approaches primarily focus on a lightweight architecture design, but neglect to further reduce network redundancy. While some model compression techniques try to achieve more lightweight SR models with neural architecture search, knowledge distillation, or channel pruning, they typically require considerable extra computational resources or neglect to prune weights. To address these issues, we propose a flexible meta pruning (FMP) for lightweight image SR, where the network channels and weights are pruned simultaneously. Specifically, we control the network sparsity via channel vectors and weight indicators. We feed them into a hypernetwork, whose parameters act as meta-data for the parameters of the SR backbone. Consequently, for each network layer, we conduct structured pruning with channel vectors, which control the output and input channels. Besides, we conduct unstructured pruning with weight indicators to influence the sparsity of kernel weights, resulting in flexible pruning. During pruning, the sparsity of both channel vectors and weight indicators are regularized. We optimize the channel vectors and weight indicators with proximal gradient and SGD. We conduct extensive experiments to investigate critical factors in the flexible channel and weight pruning for image SR, demonstrating the superiority of our FMP when applied to baseline image SR architectures.

Binarized image super-resolution (SR) has attracted much research attention due to its potential to drastically reduce parameters and operations. However, most binary SR works binarize network weights directly, which hinders high-frequency information extraction. Furthermore, as a pixel-wise reconstruction task, binarization often results in heavy representation content distortion. To address these issues, we propose a flexible residual binarization (FRB) method for image SR. We first propose a second-order residual binarization (SRB), to counter the information loss caused by binarization. In addition to the primary weight binarization, we also binarize the reconstruction error, which is added as a residual term in the prediction. Furthermore, to narrow the representation content gap between the binarized and full-precision networks, we propose Distillation-guided Binarization Training (DBT). We uniformly align the contents of different bit widths by constructing a normalized attention form. Finally, we generalize our method by applying our FRB to binarize convolution and Transformer-based SR networks, resulting in two binary baselines: FRBC and FRBT. We conduct extensive experiments and comparisons with recent leading binarization methods. Our proposed baselines, FRBC and FRBT, achieve superior performance both quantitatively and visually. The code and model will be released.

Image fusion integrates essential information from multiple images into a single composite, enhancing structures, textures, and refining imperfections. Existing methods predominantly focus on pixel-level and semantic visual features for recognition, but often overlook the deeper text-level semantic information beyond vision. Therefore, we introduce a novel fusion paradigm named image Fusion via vIsion-Language Model (FILM), for the first time, utilizing explicit textual information from source images to guide the fusion process. Specifically, FILM generates semantic prompts from images and inputs them into ChatGPT for comprehensive textual descriptions. These descriptions are fused within the textual domain and guide the visual information fusion, enhancing feature extraction and contextual understanding, directed by textual semantic information via cross-attention. FILM has shown promising results in four image fusion tasks: infrared-visible, medical, multi-exposure, and multi-focus image fusion. We also propose a vision-language dataset containing ChatGPT-generated paragraph descriptions for the eight image fusion datasets across four fusion tasks, facilitating future research in vision-language model-based image fusion. Code and dataset are available at https://github.com/Zhaozixiang1228/IF-FILM.

High dynamic range (HDR) novel view synthesis (NVS) aims to create photorealistic images from novel viewpoints using HDR imaging techniques. The rendered HDR images capture a wider range of brightness levels containing more details of the scene than normal low dynamic range (LDR) images. Existing HDR NVS methods are mainly based on NeRF. They suffer from long training time and slow inference speed. In this paper, we propose a new framework, High Dynamic Range Gaussian Splatting (HDR-GS), which can efficiently render novel HDR views and reconstruct LDR images with a user input exposure time. Specifically, we design a Dual Dynamic Range (DDR) Gaussian point cloud model that uses spherical harmonics to fit HDR color and employs an MLP-based tone-mapper to render LDR color. The HDR and LDR colors are then fed into two Parallel Differentiable Rasterization (PDR) processes to reconstruct HDR and LDR views. To establish the data foundation for the research of 3D Gaussian splatting-based methods in HDR NVS, we recalibrate the camera parameters and compute the initial positions for Gaussian point clouds. Comprehensive experiments show that HDR-GS surpasses the state-of-the-art NeRF-based method by 3.84 and 1.91 dB on LDR and HDR NVS while enjoying 1000$\times$ inference speed and only costing 6.3\% training time. Code and data are released at https://github.com/caiyuanhao1998/HDR-GS

Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating DMs. Nonetheless, due to the model structure and the multi-step iterative attribute of DMs, existing binarization methods result in significant performance degradation. In this paper, we introduce a novel binarized diffusion model, BI-DiffSR, for image SR. First, for the model structure, we design a UNet architecture optimized for binarization. We propose the consistent-pixel-downsample (CP-Down) and consistent-pixel-upsample (CP-Up) to maintain dimension consistent and facilitate the full-precision information transfer. Meanwhile, we design the channel-shuffle-fusion (CS-Fusion) to enhance feature fusion in skip connection. Second, for the activation difference across timestep, we design the timestep-aware redistribution (TaR) and activation function (TaA). The TaR and TaA dynamically adjust the distribution of activations based on different timesteps, improving the flexibility and representation alability of the binarized module. Comprehensive experiments demonstrate that our BI-DiffSR outperforms existing binarization methods. Code is released at: https://github.com/zhengchen1999/BI-DiffSR.

Exposure Correction (EC) aims to recover proper exposure conditions for images captured under over-exposure or under-exposure scenarios. While existing deep learning models have shown promising results, few have fully embedded Retinex theory into their architecture, highlighting a gap in current methodologies. Additionally, the balance between high performance and efficiency remains an under-explored problem for exposure correction task. Inspired by Mamba which demonstrates powerful and highly efficient sequence modeling, we introduce a novel framework based on \textbf{Mamba} for \textbf{E}xposure \textbf{C}orrection (\textbf{ECMamba}) with dual pathways, each dedicated to the restoration of reflectance and illumination map, respectively. Specifically, we firstly derive the Retinex theory and we train a Retinex estimator capable of mapping inputs into two intermediary spaces, each approximating the target reflectance and illumination map, respectively. This setup facilitates the refined restoration process of the subsequent \textbf{E}xposure \textbf{C}orrection \textbf{M}amba \textbf{M}odule (\textbf{ECMM}). Moreover, we develop a novel \textbf{2D S}elective \textbf{S}tate-space layer guided by \textbf{Retinex} information (\textbf{Retinex-SS2D}) as the core operator of \textbf{ECMM}. This architecture incorporates an innovative 2D scanning strategy based on deformable feature aggregation, thereby enhancing both efficiency and effectiveness. Extensive experiment results and comprehensive ablation studies demonstrate the outstanding performance and the importance of each component of our proposed ECMamba. Code is available at \url{https://github.com/LowlevelAI/ECMamba}.

Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at https://github.com/cnyvfang/CORUN-Colabator.

Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit parameters and efficient integer/bitwise constructions for storage compression and inference acceleration, respectively. However, it is notorious that low-bit quantization degrades the accuracy of SR models compared to their full-precision (FP) counterparts. Despite several efforts to alleviate the degradation, the transformer-based SR model still suffers severe degradation due to its distinctive activation distribution. In this work, we present a dual-stage low-bit post-training quantization (PTQ) method for image super-resolution, namely 2DQuant, which achieves efficient and accurate SR under low-bit quantization. The proposed method first investigates the weight and activation and finds that the distribution is characterized by coexisting symmetry and asymmetry, long tails. Specifically, we propose Distribution-Oriented Bound Initialization (DOBI), using different searching strategies to search a coarse bound for quantizers. To obtain refined quantizer parameters, we further propose Distillation Quantization Calibration (DQC), which employs a distillation approach to make the quantized model learn from its FP counterpart. Through extensive experiments on different bits and scaling factors, the performance of DOBI can reach the state-of-the-art (SOTA) while after stage two, our method surpasses existing PTQ in both metrics and visual effects. 2DQuant gains an increase in PSNR as high as 4.52dB on Set5 (x2) compared with SOTA when quantized to 2-bit and enjoys a 3.60x compression ratio and 5.08x speedup ratio. The code and models are available at https://github.com/Kai-Liu001/2DQuant.

Existing reconstruction models in snapshot compressive imaging systems (SCI) are trained with a single well-calibrated hardware instance, making their perfor- mance vulnerable to hardware shifts and limited in adapting to multiple hardware configurations. To facilitate cross-hardware learning, previous efforts attempt to directly collect multi-hardware data and perform centralized training, which is impractical due to severe user data privacy concerns and hardware heterogeneity across different platforms/institutions. In this study, we explicitly consider data privacy and heterogeneity in cooperatively optimizing SCI systems by proposing a Federated Hardware-Prompt learning (FedHP) framework. Rather than mitigating the client drift by rectifying the gradients, which only takes effect on the learning manifold but fails to solve the heterogeneity rooted in the input data space, FedHP learns a hardware-conditioned prompter to align inconsistent data distribution across clients, serving as an indicator of the data inconsistency among different hardware (e.g., coded apertures). Extensive experimental results demonstrate that the proposed FedHP coordinates the pre-trained model to multiple hardware con- figurations, outperforming prevalent FL frameworks for 0.35dB under challenging heterogeneous settings. Moreover, a Snapshot Spectral Heterogeneous Dataset has been built upon multiple practical SCI systems. Data and code are aveilable at https://github.com/Jiamian-Wang/FedHP-Snapshot-Compressive-Imaging.git

Diffusion models (DMs) have been significantly developed and widely used in various applications due to their excellent generative qualities. However, the expensive computation and massive parameters of DMs hinder their practical use in resource-constrained scenarios. As one of the effective compression approaches, quantization allows DMs to achieve storage saving and inference acceleration by reducing bit-width while maintaining generation performance. However, as the most extreme quantization form, 1-bit binarization causes the generation performance of DMs to face severe degradation or even collapse. This paper proposes a novel method, namely BiDM, for fully binarizing weights and activations of DMs, pushing quantization to the 1-bit limit. From a temporal perspective, we introduce the Timestep-friendly Binary Structure (TBS), which uses learnable activation binarizers and cross-timestep feature connections to address the highly timestep-correlated activation features of DMs. From a spatial perspective, we propose Space Patched Distillation (SPD) to address the difficulty of matching binary features during distillation, focusing on the spatial locality of image generation tasks and noise estimation networks. As the first work to fully binarize DMs, the W1A1 BiDM on the LDM-4 model for LSUN-Bedrooms 256$\times$256 achieves a remarkable FID of 22.74, significantly outperforming the current state-of-the-art general binarization methods with an FID of 59.44 and invalid generative samples, and achieves up to excellent 28.0 times storage and 52.7 times OPs savings.

Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novelLocal-GlobalAnti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available athttps://github.com/JiahuaDong/LGA.

The feature modulation mechanism has been demonstrated to be particularly well-suited for efficient network design and is rarely explored in remote sensing dehazing tasks. Moreover, we observe distinct patterns in haze distribution across the low-frequency (LF) and high-frequency (HF) components of haze images from various datasets. However, existing research rarely investigated the potential solution in the frequency domain. In response, we propose a novel spatial-frequency adaptive network (SFAN), which is mainly built by the proposed mixture of modulation experts (MoME) and decoupled frequency learning block (DFLB). Different from the fixed feature modulation design used in other tasks, the MoME adopts the mixture-of-expert mechanism to dynamically learn diverse contextual features of various granularities and scales in a sample-adaptive manner and then utilize them to perform elementwise local feature modulation. This pure convolution architecture enables our network to have superior performance and efficiency tradeoffs. Furthermore, the DFLB is devised to facilitate the LF global haze removal and reconstruction of HF local texture information. At the micro level, we first utilize a mask extractor (ME) to generate the frequency mask from the input hazy image, then employ a dual-branch decoupled learning unit to boost frequency learning, and finally develop a mixture of fusion experts (MoFE) to achieve HF and LF feature interaction. Extensive experiments on publicly available dehazing datasets demonstrate that our network performs superior performance while incurring lower computational costs. Compared to the state-of-the-art approach (DEA-Net), SFAN achieves, an average, 0.83-dB PSNR improvement on five remote sensing datasets but consumes only 51% of the FLOPs. The code will be available athttps://github.com/it-hao/SFAN.

Unpaired medical image enhancement (UMIE) aims to transform a low-quality (LQ) medical image into a high-quality (HQ) one without relying on paired images for training. While most existing approaches are based on Pix2Pix/CycleGAN and are effective to some extent, they fail to explicitly use HQ information to guide the enhancement process, which can lead to undesired artifacts and structural distortions. In this article, we propose a novel UMIE approach that avoids the above limitation of existing methods by directly encoding HQ cues into the LQ enhancement process in a variational fashion and thus model the UMIE task under the joint distribution between the LQ and HQ domains. Specifically, we extract features from an HQ image and explicitly insert the features, which are expected to encode HQ cues, into the enhancement network to guide the LQ enhancement with the variational normalization module. We train the enhancement network adversarially with a discriminator to ensure the generated HQ image falls into the HQ domain. We further propose a content-aware loss to guide the enhancement process with wavelet-based pixel-level and multiencoder-based feature-level constraints. Additionally, as a key motivation for performing image enhancement is to make the enhanced images serve better for downstream tasks, we propose a bi-level learning scheme to optimize the UMIE task and downstream tasks cooperatively, helping generate HQ images both visually appealing and favorable for downstream tasks. Experiments on three medical datasets verify that our method outperforms existing techniques in terms of both enhancement quality and downstream task performance. The code and the newly collected datasets are publicly available at https://github.com/ChunmingHe/HQG-Net.

Convolutional neural network (CNN) has achieved great success on image super-resolution (SR). However, most deep CNN-based SR models take massive computations to obtain high performance. Downsampling features for multi-resolution fusion is an efficient and effective way to improve the performance of visual recognition. Still, it is counter-intuitive in the SR task, which needs to project a low-resolution input to high-resolution. In this paper, we propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task. The network contains pixel-unshuffled downsampling and Self-Residual Depthwise Separable Convolutions. Specifically, we utilize pixel-unshuffle operation to downsample the input features and use grouped convolution to reduce the channels. Besides, we enhance the depthwise convolution's performance by adding the input feature to its output. The comparison findings demonstrate that, with fewer parameters and computational costs, our HPUN achieves and surpasses the state-of-the-art performance on SISR. All results are provided in the github https://github.com/Sun1992/HPUN.

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure for the subsequent HSI applications. Unfortunately, though witnessing the development of deep learning in HSI denoising area, existing convolution-based methods face the trade-off between computational efficiency and capability to model non-local characteristics of HSI. In this paper, we propose a Spatial-Spectral Transformer (SST) to alleviate this problem. To fully explore intrinsic similarity characteristics in both spatial dimension and spectral dimension, we conduct non-local spatial self-attention and global spectral self-attention with Transformer architecture. The window-based spatial self-attention focuses on the spatial similarity beyond the neighboring region. While, the spectral self-attention exploits the long-range dependencies between highly correlative bands. Experimental results show that our proposed method outperforms the state-of-the-art HSI denoising methods in quantitative quality and visual results. The code is released at https://github.com/MyuLi/SST.

Learning continuous image representations is recently gaining popularity for image super-resolution (SR) because of its ability to reconstruct high-resolution images with arbitrary scales from low-resolution inputs. Existing methods mostly ensemble nearby features to predict the new pixel at any queried coordinate in the SR image. Such a local ensemble suffers from some limitations: i) it has no learnable parameters and it neglects the similarity of the visual features; ii) it has a limited receptive field and cannot ensemble relevant features in a large field which are important in an image. To address these issues, this paper proposes a continuous implicit attention-in-attention network, called CiaoSR. We explicitly design an implicit attention network to learn the ensemble weights for the nearby local features. Furthermore, we embed a scale-aware attention in this implicit attention network to exploit additional non-local information. Extensive experiments on benchmark datasets demonstrate CiaoSR significantly outperforms the existing single image SR methods with the same backbone. In addition, CiaoSR also achieves the state-of-the-art performance on the arbitrary-scale SR task. The effectiveness of the method is also demonstrated on the real-world SR setting. More importantly, CiaoSR can be flexibly integrated into any backbone to improve the SR performance.

Camouflaged object detection (COD) aims to address the tough issue of identifying camouflaged objects visually blended into the surrounding backgrounds. COD is a challenging task due to the intrinsic similarity of camouflaged objects with the background, as well as their ambiguous boundaries. Existing approaches to this problem have developed various techniques to mimic the human visual system. Albeit effective in many cases, these methods still struggle when camouflaged objects are so deceptive to the vision system. In this paper, we propose the FEature Decomposition and Edge Reconstruction (FEDER) model for COD. The FEDER model addresses the intrinsic similarity of foreground and background by decomposing the features into different frequency bands using learnable wavelets. It then focuses on the most informative bands to mine subtle cues that differentiate foreground and background. To achieve this, a frequency attention module and a guidance-based feature aggregation module are developed. To combat the ambiguous boundary problem, we propose to learn an auxiliary edge reconstruction task alongside the COD task. We design an ordinary differential equation-inspired edge reconstruction module that generates exact edges. By learning the auxiliary task in conjunction with the COD task, the FEDER model can generate precise prediction maps with accurate object boundaries. Experiments show that our FEDER model significantly outperforms state-of-the-art methods with cheaper computational and memory costs. The code will be available at https://github.com/ChunmingHe/FEDER.

Denoising is a crucial step for hyperspectral image (HSI) applications. Though witnessing the great power of deep learning, existing HSI denoising methods suffer from limitations in capturing the nonlocal self-similarity. Trans-formers have shown potential in capturing longrange de-pendencies, but few attempts have been made with specifically designed Transformer to model the spatial and spec-tral correlation in HSIs. In this paper, we address these issues by proposing a spectral enhanced rectangle Trans-former, driving it to explore the nonlocal spatial similarity and global spectral low-rank property of HSIs. For the former, we exploit the rectangle self-attention horizontally and vertically to capture the nonlocal similarity in the spatial domain. For the latter, we design a spectral enhancement module that is capable of extracting global underlying low-rank property of spatial-spectral cubes to suppress noise, while enabling the interactions among non-overlapping spatial rectangles. Extensive experiments have been conducted on both synthetic noisy HSIs and real noisy HSIs, showing the effectiveness of our proposed method in terms of both objective metric and subjective visual quality. The code is available at https://github.com/MyuLi/SERT.

Despite the significant results on synthetic noise under simplified assumptions, most self-supervised denoising methods fail under real noise due to the strong spatial noise correlation, including the advanced self-supervised blindspot networks (BSNs). For recent methods targeting real-world denoising, they either suffer from ignoring this spatial correlation, or are limited by the destruction of fine textures for under-considering the correlation. In this paper, we present a novel method called LG-BPN for self-supervised real-world denoising, which takes the spatial correlation statistic into our network design for local detail restoration, and also brings the long-range dependencies modeling ability to previously CNN-based BSN methods. First, based on the correlation statistic, we propose a densely-sampled patch-masked convolution module. By taking more neighbor pixels with low noise correlation into account, we enable a denser local receptive field, preserving more useful information for enhanced fine structure recovery. Second, we propose a dilated Transformer block to allow distant context exploitation in BSN. This global perception addresses the intrinsic deficiency of BSN, whose receptive field is constrained by the blind spot requirement, which can not be fully resolved by the previous CNN-based BSNs. These two designs enable LG-BPN to fully exploit both the detailed structure and the global interaction in a blind manner. Extensive results on real-world datasets demonstrate the superior performance of our method. https://github.com/Wang-XIaoDingdd/LGBPN

The high computational costs of video super-resolution (VSR) models hinder their deployment on resource-limited devices, e.g., smartphones and drones. Existing VSR models contain considerable redundant filters, which drag down the inference efficiency. To prune these unimportant filters, we develop a structured pruning scheme called Structured Sparsity Learning (SSL) according to the properties of VSR. In SSL, we design pruning schemes for several key components in VSR models, including residual blocks, recurrent networks, and upsampling networks. Specifically, we develop a Residual Sparsity Connection (RSC) scheme for residual blocks of recurrent networks to liberate pruning restrictions and preserve the restoration information. For upsampling networks, we design a pixel-shuffle pruning scheme to guarantee the accuracy of feature channel-space conversion. In addition, we observe that pruning error would be amplified as the hidden states propagate along with recurrent networks. To alleviate the issue, we design Temporal Finetuning (TF). Extensive experiments show that SSL can significantly outperform recent methods quantitatively and qualitatively. The code is available at https://github.com/Zj-BinXia/SSL.

Multi-modality (MM) image fusion aims to render fused images that maintain the merits of different modalities, e.g., functional highlight and detailed textures. To tackle the challenge in modeling cross-modality features and decomposing desirable modality-specific and modality-shared features, we propose a novel Correlation-Driven feature Decomposition Fusion (CDDFuse) network. Firstly, CDDFuse uses Restormer blocks to extract cross-modality shallow features. We then introduce a dual-branch Transformer-CNN feature extractor with Lite Transformer (LT) blocks leveraging long-range attention to handle low-frequency global features and Invertible Neural Networks (INN) blocks focusing on extracting high-frequency local information. A correlation-driven loss is further proposed to make the low-frequency features correlated while the high-frequency features uncorrelated based on the embedded information. Then, the LT-based global fusion and INN-based local fusion layers output the fused image. Extensive experiments demonstrate that our CDDFuse achieves promising results in multiple fusion tasks, including infrared-visible image fusion and medical image fusion. We also show that CDDFuse can boost the performance in downstream infrared-visible semantic segmentation and object detection in a unified benchmark. The code is available at https://github.om/haozixiang1228/MMIF-CDDFuse.

Transformer has recently gained considerable popularity in low-level vision tasks, including image super-resolution (SR). These networks utilize self-attention along different dimensions, spatial or channel, and achieve impressive performance. This inspires us to combine the two dimensions in Transformer for a more powerful representation capability. Based on the above idea, we propose a novel Transformer model, Dual Aggregation Transformer (DAT), for image SR. Our DAT aggregates features across spatial and channel dimensions, in the inter-block and intra-block dual manner. Specifically, we alternately apply spatial and channel self-attention in consecutive Transformer blocks. The alternate strategy enables DAT to capture the global context and realize inter-block feature aggregation. Furthermore, we propose the adaptive interaction module (AIM) and the spatial-gate feed-forward network (SGFN) to achieve intra-block feature aggregation. AIM complements two self-attention mechanisms from corresponding dimensions. Meanwhile, SGFN introduces additional non-linear spatial information in the feed-forward network. Extensive experiments show that our DAT surpasses current methods. Code and models are obtainable at https://github.com/zhengchen1999/DAT.

When enhancing low-light images, many deep learning algorithms are based on the Retinex theory. However, the Retinex model does not consider the corruptions hidden in the dark or introduced by the light-up process. Besides, these methods usually require a tedious multi-stage training pipeline and rely on convolutional neural networks, showing limitations in capturing long-range dependencies. In this paper, we formulate a simple yet principled One-stage Retinex-based Framework (ORF). ORF first estimates the illumination information to light up the low-light image and then restores the corruption to produce the enhanced image. We design an Illumination-Guided Transformer (IGT) that utilizes illumination representations to direct the modeling of non-local interactions of regions with different lighting conditions. By plugging IGT into ORF, we obtain our algorithm, Retinexformer. Comprehensive quantitative and qualitative experiments demonstrate that our Retinexformer significantly outperforms state-of-the-art methods on thirteen benchmarks. The user study and application on low-light object detection also reveal the latent practical values of our method. Code is available at https://github.com/caiyuanhao1998/Retinexformer

Heterogeneous image fusion (HIF) techniques aim to enhance image quality by merging complementary information from images captured by different sensors. Among these algorithms, deep unfolding network (DUN)-based methods achieve promising performance but still suffer from two issues: they lack a degradation-resistant-oriented fusion model and struggle to adequately consider the structural properties of DUNs, making them vulnerable to degradation scenarios. In this paper, we propose a Degradation-Resistant Unfolding Network (DeRUN) for the HIF task to generate high-quality fused images even in degradation scenarios. Specifically, we introduce a novel HIF model for degradation resistance and derive its optimization procedures. Then, we incorporate the optimization unfolding process into the proposed DeRUN for end-to-end training. To ensure the robustness and efficiency of DeRUN, we employ a joint constraint strategy and a lightweight partial weight sharing module. To train DeRUN, we further propose a gradient direction-based entropy loss with powerful texture representation capacity. Extensive experiments show that DeRUN significantly outperforms existing methods on four HIF tasks, as well as downstream applications, with cheaper computational and memory costs.

Hyperspectral Image (HSI) reconstruction has made gratifying progress with the deep unfolding framework by formulating the problem into a data module and a prior module. Nevertheless, existing methods still face the problem of insufficient matching with HSI data. The issues lie in three aspects: 1) fixed gradient descent step in the data module while the degradation of HSI is agnostic in the pixel-level. 2) inadequate prior module for 3D HSI cube. 3) stage interaction ignoring the differences in features at different stages. To address these issues, in this work, we propose a Pixel Adaptive Deep Unfolding Transformer (PADUT) for HSI reconstruction. In the data module, a pixel adaptive descent step is employed to focus on pixel-level agnostic degradation. In the prior module, we introduce the Non-local Spectral Transformer (NST) to emphasize the 3D characteristics of HSI for recovering. Moreover, inspired by the diverse expression of features in different stages and depths, the stage interaction is improved by the Fast Fourier Transform (FFT). Experimental results on both simulated and real scenes exhibit the superior performance of our method compared to state-of-the-art HSI reconstruction methods. The code is released at: https://github.com/MyuLi/PADUT

High dynamic range (HDR) imaging aims to retrieve information from multiple low-dynamic range inputs to generate realistic output. The essence is to leverage the contextual information, including both dynamic and static semantics, for better image generation. Existing methods often focus on the spatial misalignment across input frames caused by the foreground and/or camera motion. However, there is no research on jointly leveraging the dynamic and static context in a simultaneous manner. To delve into this problem, we propose a novel alignment-free network with a Semantics Consistent Transformer (SCTNet) with both spatial and channel attention modules in the network. The spatial attention aims to deal with the intra-image correlation to model the dynamic motion, while the channel attention enables the inter-image intertwining to enhance the semantic consistency across frames. Aside from this, we introduce a novel realistic HDR dataset with more variations in foreground objects, environmental factors, and larger motions. Extensive comparisons on both conventional datasets and ours validate the effectiveness of our method, achieving the best trade-off on the performance and the computational cost. The source code and dataset are available at https://steven-tel.github.io/sctnet/.

Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. However, prevailing SR models suffer from prohibitive memory footprint and intensive computations, which limits further deployment on edge devices. This work investigates the potential of network pruning for super-resolution to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. Two main challenges remain in applying pruning methods for SR. First, the widely-used filter pruning technique reflects limited granularity and restricted adaptability to diverse network structures. Second, existing pruning methods generally operate upon a pre-trained network for the sparse structure determination, hard to get rid of dense model training in the traditional SR paradigm. To address these challenges, we adopt unstructured pruning with sparse models directly trained from scratch. Specifically, we propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly initialized network at each iteration and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly. We observe that the proposed ISS-P can dynamically learn sparse structures adapting to the optimization process and preserve the sparse model’s trainability by yielding a more regularized gradient throughput. Experiments on benchmark datasets demonstrate the effectiveness of the proposed ISS-P over diverse network architectures. Code is available at https://github.com/Jiamian-Wang/Iterative-Soft-Shrinkage-SR

Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis, image restoration (IR) has a strong constraint to generate results in accordance with ground-truth. Thus, for IR, traditional DMs running massive iterations on a large model to estimate whole images or feature maps is inefficient. To address this issue, we propose an efficient DM for IR (DiffIR), which consists of a compact IR prior extraction network (CPEN), dynamic IR transformer (DIRformer), and denoising network. Specifically, DiffIR has two training stages: pretraining and training DM. In pretraining, we input ground-truth images into CPENS1to capture a compact IR prior representation (IPR) to guide DIRformer. In the second stage, we train the DM to directly estimate the same IRP as pretrained CPENS1only using LQ images. We observe that since the IPR is only a compact vector, DiffIR can use fewer iterations than traditional DM to obtain accurate estimations and generate more stable and realistic results. Since the iterations are few, our DiffIR can adopt a joint optimization of CPENS2, DIRformer, and denoising network, which can further reduce the estimation error influence. We conduct extensive experiments on several IR tasks and achieve SOTA performance while consuming less computational costs. Code is available at https://github.com/Zj-BinXia/DiffIR.

Guided depth map super-resolution (GDSR), as a hot topic in multi-modal image processing, aims to upsample low-resolution (LR) depth maps with additional information involved in high-resolution (HR) RGB images from the same scene. The critical step of this task is to effectively extract domain-shared and domain-private RGB/depth features. In addition, three detailed issues, namely blurry edges, noisy surfaces, and over-transferred RGB texture, need to be addressed. In this paper, we propose the Spherical Space feature Decomposition Network (SSDNet) to solve the above issues. To better model cross-modality features, Restormer block-based RGB/depth encoders are employed for extracting local-global features. Then, the extracted features are mapped to the spherical space to complete the separation of private features and the alignment of shared features. Shared features of RGB are fused with the depth features to complete the GDSR task. Subsequently, a spherical contrast refinement (SCR) module is proposed to further address the detail issues. Patches that are classified according to imperfect categories are input into the SCR module, where the patch features are pulled closer to the ground truth and pushed away from the corresponding imperfect samples in the spherical feature space via contrastive learning. Extensive experiments demonstrate that our method can achieve state-of-the-art results on four test datasets, as well as successfully generalize to real-world scenes. The code is available at https://github.com/Zhaozixiang1228/GDSR-SSDNet.

Multi-modality image fusion aims to combine different modalities to produce fused images that retain the complementary features of each modality, such as functional highlights and texture details. To leverage strong generative priors and address challenges such as unstable training and lack of interpretability for GAN-based generative methods, we propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM). The fusion task is formulated as a conditional generation problem under the DDPM sampling framework, which is further divided into an unconditional generation subproblem and a maximum likelihood subproblem. The latter is modeled in a hierarchical Bayesian manner with latent variables and inferred by the expectation-maximization (EM) algorithm. By integrating the inference solution into the diffusion sampling iteration, our method can generate high-quality fused images with natural image generative priors and cross-modality information from source images. Note that all we required is an unconditional pre-trained generative model, and no fine-tuning is needed. Our extensive experiments indicate that our approach yields promising fusion results in infrared-visible image fusion and medical image fusion. The code is available at https://github.com/Zhaozixiang1228/MMIF-DDFM.

Adaptive gradient methods, e.g., ADAM, have achieved tremendous success in data-driven machine learning, especially deep learning. Employing adaptive learning rates according to the gradients, such methods are able to attain rapid training of modern deep neural networks. Nevertheless, they are observed to suffer from compromised generalization capacity compared with stochastic gradient descent (SGD) and tend to be trapped in local minima at an early stage during the training process. Intriguingly, we discover that the issue can be resolved by substituting the gradient in the second raw moment estimate term with its exponential moving average version in ADAM. The intuition is that the gradient with momentum contains more accurate directional information, and therefore its second-moment estimation is a more preferable option for learning rate scaling than that of the raw gradient. Thereby we propose ADAM$^{3}$ as a new optimizer reaching the goal of training quickly while generalizing much better. Extensive experiments on a variety of tasks and models demonstrate that ADAM$^{3}$ exhibits state-of-the-art performance and superior training stability consistently. Considering the simplicity and effectiveness of ADAM$^{3}$, we believe it has the potential to become a new standard method in deep learning. Code is provided at https://github.com/wyzjack/AdaM3.

Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range degradations to enhance generalization, a decline in accuracy is inevitable. However, since the degradation in a certain real-world applications typically exhibits a limited variation range, it becomes feasible to strike a trade-off between generalization performance and testing accuracy within this scope. In this work, we introduce a novel approach to craft training degradation distributions using a small set of reference images. Our strategy is founded upon the binned representation of the degradation space and the Frechet distance between degradation distributions. Our results indicate that the proposed technique significantly improves the performance of test images while preserving generalization capabilities in real-world applications.

Multi-stage architectures have exhibited efficacy in image dehazing, which usually decomposes a challenging task into multiple more tractable sub-tasks and progressively estimates latent hazy-free images. Despite the remarkable progress, existing methods still suffer from the following shortcomings: (1) limited exploration of frequency domain information; (2) insufficient information interaction; (3) severe feature redundancy. To remedy these issues, we propose a novel Mutual Information-driven Triple interaction Network (MITNet) based on spatial-frequency dual domain information and two-stage architecture. To be specific, the first stage, named amplitude-guided haze removal, aims to recover the amplitude spectrum of the hazy images for haze removal. And the second stage, named phase-guided structure refined, devotes to learning the transformation and refinement of the phase spectrum. To facilitate the information exchange between two stages, an Adaptive Triple Interaction Module (ATIM) is developed to simultaneously aggregate cross-domain, cross-scale, and cross-stage features, where the fused features are further used to generate content-adaptive dynamic filters so that applying them to enhance global context representation. In addition, we impose the mutual information minimization constraint on paired scale encoder and decoder features from both stages. Such an operation can effectively reduce information redundancy and enhance cross-stage feature complementarity. Extensive experiments on multiple public datasets exhibit that our MITNet performs superior performance with lower model complexity. The code and models are available at https://github.com/it-hao/MITNet.

Self-supervised video denoising has seen decent progress through the use of blind spot networks. However, under their blind spot constraints, previous self-supervised video denoising methods suffer from significant information loss and texture destruction in either the whole reference frame or neighbor frames, due to their inadequate consideration of the receptive field. Moreover, the limited number of available neighbor frames in previous methods leads to the discarding of distant temporal information. Nonetheless, simply adopting existing recurrent frameworks does not work, since they easily break the constraints on the receptive field imposed by self-supervision. In this paper, we propose RDRF for selfsupervised video denoising, which not only fully exploits both the reference and neighbor frames with a denser receptive field, but also better leverages the temporal information from both local and distant neighbor features. First, towards a comprehensive utilization of information from both reference and neighbor frames, RDRF realizes a denser receptive field by taking more neighbor pixels along the spatial and temporal dimensions. Second, it features a self-supervised recurrent video denoising framework, which concurrently integrates distant and near-neighbor temporal features. This enables long-term bidirectional information aggregation, while mitigating error accumulation in the plain recurrent framework. Our method exhibits superior performance on both synthetic and real video denoising datasets. Codes will be available at https://github.com/Wang-XIaoDingdd/RDRF.

Existing deep learning models for hyperspectral image (HSI) reconstruction achieve good performance but require powerful hardwares with enormous memory and computational resources. Consequently, these methods can hardly be deployed on resource-limited mobile devices. In this paper, we propose a novel method, Binarized Spectral-Redistribution Network (BiSRNet), for efficient and practical HSI restoration from compressed measurement in snapshot compressive imaging (SCI) systems. Firstly, we redesign a compact and easy-to-deploy base model to be binarized. Then we present the basic unit, Binarized Spectral-Redistribution Convolution (BiSR-Conv). BiSR-Conv can adaptively redistribute the HSI representations before binarizing activation and uses a scalable hyperbolic tangent function to closer approximate the Sign function in backpropagation. Based on our BiSR-Conv, we customize four binarized convolutional modules to address the dimension mismatch and propagate full-precision information throughout the whole network. Finally, our BiSRNet is derived by using the proposed techniques to binarize the base model. Comprehensive quantitative and qualitative experiments manifest that our proposed BiSRNet outperforms state-of-the-art binarization algorithms. Code and models are publicly available at https://github.com/caiyuanhao1998/BiSCI

Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to recover the clean image from pure Gaussian noise, which consumes massive computational resources. Moreover, the distribution synthesized by the diffusion model is often misaligned with the target results, leading to restrictions in distortion-based metrics. To address the above issues, we propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process. The deblurring process is implemented by a regression-based method to obtain better distortion accuracy. Meanwhile, the highly compact latent space ensures the efficiency of the DM. Furthermore, we design the hierarchical integration module to fuse the prior into the regression-based model from multiple scales, enabling better generalization in complex blurry scenarios. Comprehensive experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods. Code and trained models are available at https://github.com/zhengchen1999/HI-Diff.

Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment objects well blended with surrounding environments using sparsely-annotated data for model training. It remains a challenging task since (1) it is hard to distinguish concealed objects from the background due to the intrinsic similarity and (2) the sparsely-annotated training data only provide weak supervision for model learning. In this paper, we propose a new WSCOS method to address these two challenges. To tackle the intrinsic similarity challenge, we design a multi-scale feature grouping module that first groups features at different granularities and then aggregates these grouping results. By grouping similar features together, it encourages segmentation coherence, helping obtain complete segmentation results for both single and multiple-object images. For the weak supervision challenge, we utilize the recently-proposed vision foundation model, ``Segment Anything Model (SAM)'', and use the provided sparse annotations as prompts to generate segmentation masks, which are used to train the model. To alleviate the impact of low-quality segmentation masks, we further propose a series of strategies, including multi-augmentation result ensemble, entropy-based pixel-level weighting, and entropy-based image-level selection. These strategies help provide more reliable supervision to train the segmentation model. We verify the effectiveness of our method on various WSCOS tasks, and experiments demonstrate that our method achieves state-of-the-art performance on these tasks.

Low-bit quantization in image super-resolution (SR) has attracted copious attention in recent research due to its ability to reduce parameters and operations significantly. However, many quantized SR models suffer from accuracy degradation compared to their full-precision counterparts, especially at ultra-low bit widths (2-4 bits), limiting their practical applications. To address this issue, we propose a novel quantized image SR network, called QuantSR, which achieves accurate and efficient SR processing under low-bit quantization. To overcome the representation homogeneity caused by quantization in the network, we introduce the Redistribution-driven Learnable Quantizer (RLQ). This is accomplished through an inference-agnostic efficient redistribution design, which adds additional information in both forward and backward passes to improve the representation ability of quantized networks. Furthermore, to achieve flexible inference and break the upper limit of accuracy, we propose the Depth-dynamic Quantized Architecture (DQA). Our DQA allows for the trade-off between efficiency and accuracy during inference through weight sharing. Our comprehensive experiments show that QuantSR outperforms existing state-of-the-art quantized SR networks in terms of accuracy while also providing more competitive computational efficiency. In addition, we demonstrate the scheme's satisfactory architecture generality by providing QuantSR-C and QuantSR-T for both convolution and Transformer versions, respectively. Our code and models are released at https://github.com/htqin/QuantSR .

Abstract Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales. However, recent advanced deep convolutional neural network-based methods for image restoration do not take full advantage of self-similarities by relying on self-attention neural modules that only process information at the same scale. To solve this problem, we present a novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid. Inspired by the fact that corruptions, such as noise or compression artifacts, drop drastically at coarser image scales, our attention module is designed to be able to borrow clean signals from their “clean” correspondences at the coarser levels. The proposed pyramid attention module is a generic building block that can be flexibly integrated into various neural architectures. Its effectiveness is validated through extensive experiments on multiple image restoration tasks: image denoising, demosaicing, compression artifact reduction, and super resolution. Without any bells and whistles, our PANet (pyramid attention module with simple network backbones) can produce state-of-the-art results with superior accuracy and visual quality. Our code is available at https://github.com/SHI-Labs/Pyramid-Attention-Networks

As a bridge between language and vision domains, cross-modal retrieval between images and texts is a hot research topic in recent years. It remains challenging because the current image representations usually lack semantic concepts in the corresponding sentence captions. To address this issue, we introduce an intuitive and interpretable model to learn a common embedding space for alignments between images and text descriptions. Specifically, our model first incorporates the semantic relationship information into visual and textual features by performing region or word relationship reasoning. Then it utilizes the gate and memory mechanism to perform global semantic reasoning on these relationship-enhanced features, select the discriminative information and gradually grow representations for the whole scene. Through the alignment learning, the learned visual representations capture key objects and semantic concepts of a scene as in the corresponding text caption. Experiments on MS-COCO [1] and Flickr30K [2] datasets validate that our method surpasses many recent state-of-the-arts with a clear margin. In addition to the effectiveness, our methods are also very efficient at the inference stage. Thanks to the effective overall representation learning with visual semantic reasoning, our methods can already achieve very strong performance by only relying on the simple inner-product to obtain similarity scores between images and captions. Experiments validate the proposed methods are more than 30-75 times faster than many recent methods with code public available. Instead of following the recent trend of using complex local matching strategies [3], [4], [5], [6] to pursue good performance while sacrificing efficiency, we show that the simple global matching strategy can still be very effective, efficient and achieve even better performance based on our framework.

Deep learning has made unprecedented progress in image restoration (IR), where residual block (RB) is popularly used and has a significant effect on promising performance. However, the massive stacked RBs bring about burdensome memory and computation cost. To tackle this issue, we aim to design an economical structure for adaptively connecting pair-wise RBs, thereby enhancing the model representation. Inspired by the topological structure of lattice filter in signal processing theory, we elaborately propose the lattice block (LB), where couple butterfly-style topological structures are utilized to bridge pair-wise RBs. Specifically, each candidate structure of LB relies on the combination coefficients learned through adaptive channel reweighting. As a basic mapping block, LB can be plugged into various IR models, such as image super-resolution, image denoising, image deraining, etc. It can avail the construction of lightweight IR models accompanying half parameter amount reduced, while keeping the considerable reconstruction accuracy compared with RBs. Moreover, a novel contrastive loss is exploited as a regularization constraint, which can further enhance the model representation without increasing the inference expenses. Experiments on several IR tasks illustrate that our method can achieve more favorable performance than other state-of-the-art models with lower storage and computation.

Efficient image super-resolution (SR) has witnessed rapid progress thanks to novel lightweight architectures or model compression techniques (e.g., neural architecture search and knowledge distillation). Nevertheless, these methods consume considerable resources or/and neglect to squeeze out the network redundancy at a more fine-grained convolution filter level. Network pruning is a promising alternative to overcome these shortcomings. However, structured pruning is known to be tricky when applied to SR networks because the extensive residual blocks demand the pruned indices of different layers to be the same. Besides, the principled determination of proper layerwise sparsities remains challenging too. In this article, we present Global Aligned Structured Sparsity Learning (GASSL) to resolve these problems. GASSL has two major components: Hessian-Aided Regularization (HAIR) and Aligned Structured Sparsity Learning (ASSL). HAIR is a regularization-based sparsity auto-selection algorithm with Hessian considered implicitly. A proven proposition is introduced to justify its design. ASSL is for physically pruning SR networks. Particularly, a new penalty term Sparsity Structure Alignment (SSA) is proposed to align the pruned indices of different layers. With GASSL, we design two new efficient single image SR networks of different architecture genres, pushing the efficiency envelope of SR models one step forward. Extensive results demonstrate the merits of GASSL over other recent counterparts.

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model so that the image can be faithfully reconstructed from the inverted code by the generator. As an emerging technique to bridge the real and fake image domains, GAN inversion plays an essential role in enabling pretrained GAN models, such as StyleGAN and BigGAN, for applications of real image editing. Moreover, GAN inversion interprets GAN's latent space and examines how realistic images can be generated. In this paper, we provide a survey of GAN inversion with a focus on its representative algorithms and its applications in image restoration and image manipulation. We further discuss the trends and challenges for future research. A curated list of GAN inversion methods, datasets, and other related information can be found at https://github.com/weihaox/awesome-gan-inversion.

We address the problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression. Many recent works utilize Transformer to extract features for the target object by aggregating the attended visual regions. However, the generic attention mechanism in Transformer only uses the language input for attention weight calculation, which does not explicitly fuse language features in its output. Thus, its output feature is dominated by vision information, which limits the model to comprehensively understand the multi-modal information, and brings uncertainty for the subsequent mask decoder to extract the output mask. To address this issue, we propose Multi-Modal Mutual Attention (M3Att) and Multi-Modal Mutual Decoder (M3Dec) that better fuse information from the two input modalities. Based on M3Dec, we further propose Iterative Multi-modal Interaction (IMI) to allow continuous and in-depth interactions between language and vision features. Furthermore, we introduce Language Feature Reconstruction (LFR) to prevent the language information from being lost or distorted in the extracted feature. Extensive experiments show that our proposed approach significantly improves the baseline and outperforms state-of-the-art referring image segmentation methods on RefCOCO series datasets consistently.

Blind image super-resolution (blind SR) aims to generate high-resolution (HR) images from low-resolution (LR) input images with unknown degradations. To enhance the performance of SR, the majority of blind SR methods introduce an explicit degradation estimator, which helps the SR model adjust to unknown degradation scenarios. Unfortunately, it is impractical to provide concrete labels for the multiple combinations of degradations (e.g., blurring, noise, or JPEG compression) to guide the training of the degradation estimator. Moreover, the special designs for certain degradations hinder the models from being generalized for dealing with other degradations. Thus, it is imperative to devise an implicit degradation estimator that can extract discriminative degradation representations for all types of degradations without requiring the supervision of degradation ground-truth. To this end, we propose a Meta-Learning based Region Degradation Aware SR Network (MRDA), including Meta-Learning Network (MLN), Degradation Extraction Network (DEN), and Region Degradation Aware SR Network (RDAN). To handle the lack of ground-truth degradation, we use the MLN to rapidly adapt to the specific complex degradation after several iterations and extract implicit degradation information. Subsequently, a teacher network MRDAT is designed to further utilize the degradation information extracted by MLN for SR. However, MLN requires iterating on paired LR and HR images, which is unavailable in the inference phase. Therefore, we adopt knowledge distillation (KD) to make the student network learn to directly extract the same implicit degradation representation (IDR) as the teacher from LR images. Furthermore, we introduce an RDAN module that is capable of discerning regional degradations, allowing IDR to adaptively influence various texture patterns. Extensive experiments under classic and real-world degradation settings show that MRDA achieves SOTA performance and can generalize to various degradation processes.

Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement in the coded aperture snapshot spectral imaging (CASSI) system. The HSI representations are highly similar and correlated across the spectral dimension. Modeling the inter-spectra interactions is beneficial for HSI reconstruction. However, existing CNN-based methods show limitations in capturing spectral-wise similarity and long-range dependencies. Besides, the HSI information is modulated by a coded aperture (physical mask) in CASSI. Nonetheless, current algorithms have not fully explored the guidance effect of the mask for HSI restoration. In this paper, we propose a novel framework, Mask-guided Spectral-wise Transformer (MST), for HSI reconstruction. Specifically, we present a Spectral-wise Multi-head Self-Attention (S-MSA) that treats each spectral feature as a token and calculates self-attention along the spectral dimension. In addition, we customize a Mask-guided Mechanism (MM) that directs S- MSA to pay attention to spatial regions with high-fidelity spectral representations. Extensive experiments show that our MST significantly outperforms state-of-the-art (SOTA) methods on simulation and real HSI datasets while requiring dramatically cheaper computational and memory costs. https://github.com/caiyuanhao1998/MST/

The rapid development of deep learning provides a better solution for the end-to-end reconstruction of hyperspectral image (HSI). However, existing learning-based methods have two major defects. Firstly, networks with self-attention usually sacrifice internal resolution to balance model performance against complexity, losing fine-grained high-resolution (HR) features. Secondly, even if the optimization focusing on spatial-spectral domain learning (SDL) converges to the ideal solution, there is still a significant visual difference between the reconstructed HSI and the truth. So we propose a high-resolution dual-domain learning network (HDNet) for HSI reconstruction. On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features. On the other hand, frequency domain learning (FDL) is introduced for HSI reconstruction to narrow the frequency domain discrepancy. Dynamic FDL supervision forces the model to reconstruct fine-grained frequencies and compensate for excessive smoothing and distortion caused by pixel-level losses. The HR pixel-level attention and frequency-level refinement in our HDNet mutually promote HSI perceptual quality. Extensive quantitative and qualitative experiments show that our method achieves SOTA performance on simulated and real HSI datasets. https://github.com/Huxiaowan/HDNet

Evaluation practices for image super-resolution (SR) use a single-value metric, the PSNR or SSIM, to determine model performance. This provides little insight into the source of errors and model behavior. Therefore, it is beneficial to move beyond the conventional approach and reconceptualize evaluation with interpretability as our main priority. We focus on a thorough error analysis from a variety of perspectives. Our key contribution is to leverage a texture classifier, which enables us to assign patches with semantic labels, to identify the source of SR errors both globally and locally. We then use this to determine (a) the semantic alignment of SR datasets, (b) how SR models perform on each label, (c) to what extent high-resolution (HR) and SR patches semantically correspond, and more. Through these different angles, we are able to highlight potential pitfalls and blindspots. Our overall investigation highlights numerous unexpected insights. We hope this work serves as an initial step for debugging blackbox SR networks.

Anomaly Detection (AD) aims to find defective patterns or abnormal samples among data, and has been a hot research topic due to various real-world applications. While various AD methods have been proposed, most of them assume the availability of a clean (anomaly-free) training set, which however may be hard to guarantee in many real-world industry applications. This motivates us to investigate Unsupervised Anomaly Detection (UAD) in which the training set includes both normal and abnormal samples. In this paper, we address the UAD problem by proposing a Self-Training and Knowledge Distillation (STKD) model. STKD combats anomalies in the training set by iteratively alternating between excluding samples of high anomaly probabilities and training the model with the purified training set. Despite that the model is trained with a cleaner training set, the inevitably existing anomalies may still cause negative impact. STKD alleviates this by regularizing the model to respond similarly to a teacher model which has not been trained with noisy data. Experiments show that STKD consistently produces more robust performance with different levels of anomalies.

Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range dependencies and modeling non-local self-similarity. In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring. In FGST, we customize a self-attention module, Flow-Guided Sparse Window-based Multi-head Self-Attention (FGSW-MSA). For each $query$ element on the blurry reference frame, FGSW-MSA enjoys the guidance of the estimated optical flow to globally sample spatially sparse yet highly related $key$ elements corresponding to the same scene patch in neighboring frames. Besides, we present a Recurrent Embedding (RE) mechanism to transfer information from past frames and strengthen long-range temporal dependencies. Comprehensive experiments demonstrate that our proposed FGST outperforms state-of-the-art (SOTA) methods on both DVD and GOPRO datasets and yields visually pleasant results in real video deblurring. https://github.com/linjing7/VR-Baseline

How to properly model the inter-frame relation within the video sequence is an important but unsolved challenge for video restoration (VR). In this work, we propose an unsupervised flow-aligned sequence-to-sequence model (S2SVR) to address this problem. On the one hand, the sequence-to-sequence model, which has proven capable of sequence modeling in the field of natural language processing, is explored for the first time in VR. Optimized serialization modeling shows potential in capturing long-range dependencies among frames. On the other hand, we equip the sequence-to-sequence model with an unsupervised optical flow estimator to maximize its potential. The flow estimator is trained with our proposed unsupervised distillation loss, which can alleviate the data discrepancy and inaccurate degraded optical flow issues of previous flow-based methods. With reliable optical flow, we can establish accurate correspondence among multiple frames, narrowing the domain difference between 1D language and 2D misaligned frames and improving the potential of the sequence-to-sequence model. S2SVR shows superior performance in multiple VR tasks, including video deblurring, video super-resolution, and compressed video quality enhancement. https://github.com/linjing7/VR-Baseline

Few-shot learning aims to enable models generalize to new categories (query instances) with only limited labeled samples (support instances) from each category. Metric-based mechanism is a promising direction which compares feature embeddings via different metrics. However, it always fail to generalize to unseen domains due to the considerable domain gap challenge. In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning. Specifically, an instance normalization algorithm is explored to alleviate feature dissimilarity, which provides the initial model generalization ability. However, naively normalizing the feature would lose fine-grained discriminative knowledge between different classes. To this end, a memorized module is further proposed to separate the most refined knowledge and remember it. Then, a restitution module is utilized to restitute the discrimination ability from the learned knowledge. A novel reverse contrastive learning strategy is proposed to stabilize the distillation process. Extensive experiments on five popular benchmark datasets demonstrate that MemREIN well addresses the domain shift challenge, and significantly improves the performance up to 16.43% compared with state-of-the-art baselines.

Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network. This paper offers the first survey concentrated on this emerging pruning fashion. We first introduce a generic formulation of neural network pruning, followed by the major classic pruning topics. Then, as the main body of this paper, a thorough and structured literature review of PaI methods is presented, consisting of two major tracks (sparse training and sparse selection). Finally, we summarize the surge of PaI compared to PaT and discuss the open problems. Apart from the dedicated literature review, this paper also offers a code base for easy sanity-checking and benchmarking of different PaI methods.

Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis. Higher resolution helps to capture more detailed content, but typically induces to lower signal-to-noise ratio and longer scanning time. To this end, MR image super-resolution has become a widely-interested topic in recent times. Existing works establish extensive deep models with the conventional architectures based on convolutional neural networks (CNN). In this work, to further advance this research field, we make an early effort to build a Transformer-based MR image super-resolution framework, with careful designs on exploring valuable domain prior knowledge. Specifically, we consider two-fold domain priors including the high-frequency structure prior and the inter-modality context prior, and establish a novel Transformer architecture, called Cross-modality high-frequency Transformer (Cohf-T), to introduce such priors into super-resolving the low-resolution (LR) MR images. Experiments on two datasets indicate that Cohf-T achieves new state-of-the-art performance.

Though single image super-resolution (SR) has witnessed incredible progress, the increasing model complexity impairs its applications in memory-limited devices. To solve this problem, prior arts have aimed to reduce the number of model parameters and sparsity has been exploited, which usually enforces the group sparsity constraint on the filter level and thus is not arbitrarily adjustable for satisfying the customized memory requirements. In this paper, we propose an individual kernel sparsity (IKS) method for memory-efficient and sparsity-adjustable image SR to aid deep network deployment in memory-limited devices. IKS performs model sparsity in the weight level that implicitly allocates the user-defined target sparsity to each individual kernel. To induce the kernel sparsity, a soft thresholding operation is used as a gating constraint for filtering the trivial weights. To achieve adjustable sparsity, a dynamic threshold learning algorithm is proposed, in which the threshold is updated by associated training with the network weight and is adaptively decayed with the guidance of the desired sparsity. This work essentially provides a dynamic parameter reassignment scheme with a given resource budget for an off-the-shelf SR model. Extensive experimental results demonstrate that IKS imparts considerable sparsity with negligible effect on SR quality. The code is available at: https://github.com/RaccoonDML/IKS.

In coded aperture snapshot spectral compressive imaging (CASSI) systems, hyperspectral image (HSI) reconstruction methods are employed to recover the spatial-spectral signal from a compressed measurement. Among these algorithms, deep unfolding methods demonstrate promising performance but suffer from two issues. Firstly, they do not estimate the degradation patterns and ill-posedness degree from CASSI to guide the iterative learning. Secondly, they are mainly CNN-based, showing limitations in capturing long-range dependencies. In this paper, we propose a principled Degradation-Aware Unfolding Framework (DAUF) that estimates parameters from the compressed image and physical mask, and then uses these parameters to control each iteration. Moreover, we customize a novel Half-Shuffle Transformer (HST) that simultaneously captures local contents and non-local dependencies. By plugging HST into DAUF, we establish the first Transformer-based deep unfolding method, Degradation-Aware Unfolding Half-Shuffle Transformer (DAUHST), for HSI reconstruction. Experiments show that DAUHST surpasses state-of-the-art methods while requiring cheaper computational and memory costs. Code and models are publicly available at https://github.com/caiyuanhao1998/MST

Recently, Transformer architecture has been introduced into image restoration to replace convolution neural network (CNN) with surprising results. Considering the high computational complexity of Transformer with global attention, some methods use the local square window to limit the scope of self-attention. However, these methods lack direct interaction among different windows, which limits the establishment of long-range dependencies. To address the above issue, we propose a new image restoration model, Cross Aggregation Transformer (CAT). The core of our CAT is the Rectangle-Window Self-Attention (Rwin-SA), which utilizes horizontal and vertical rectangle window attention in different heads parallelly to expand the attention area and aggregate the features cross different windows. We also introduce the Axial-Shift operation for different window interactions. Furthermore, we propose the Locality Complementary Module to complement the self-attention mechanism, which incorporates the inductive bias of CNN (e.g., translation invariance and locality) into Transformer, enabling global-local coupling. Extensive experiments demonstrate that our CAT outperforms recent state-of-the-art methods on several image restoration applications. The code and models are available at https://github.com/zhengchen1999/CAT.

High-quality magnetic resonance (MR) images afford more detailed information for reliable diagnoses and quantitative image analyses. Given low-resolution (LR) images, the deep convolutional neural network (CNN) has shown its promising ability for image super-resolution (SR). The LR MR images usually share some visual characteristics: structural textures of different sizes, edges with high correlation, and less informative background. However, multi-scale structural features are informative for image reconstruction, while the background is more smooth. Most previous CNN-based SR methods use a single receptive field and equally treat the spatial pixels (including the background). It neglects to sense the entire space and get diversified features from the input, which is critical for high-quality MR image SR. We propose a wide weighted attention multi-scale network ($\text{W}^{2}$AMSN) for accurate MR image SR to address these problems. On the one hand, the features of varying sizes can be extracted by the wide multi-scale branches. On the other hand, we design a non-reduction attention mechanism to recalibrate feature responses adaptively. Such attention preserves continuous cross-channel interaction and focuses on more informative regions. Meanwhile, the learnable weighted factors fuse extracted features selectively. The encapsulated wide weighted attention multi-scale block ($\text{W}^{2}$AMSB) is integrated through a recurrent framework and global attention mechanism. Extensive experiments and diversified ablation studies show the effectiveness of our proposed$\text{W}^{2}$AMSN, which surpasses state-of-the-art methods on most popular MR image SR benchmarks quantitatively and qualitatively. And our method still offers superior accuracy and adaptability on real MR images.

Multiview subspace clustering (MVSC) leverages the complementary information among different views of multiview data and seeks a consensus subspace clustering result better than that using any individual view. Though proved effective in some cases, existing MVSC methods often obtain unsatisfactory results since they perform subspace analysis with raw features that are often of high dimensions and contain noises. To remedy this, we propose a self-guided deep multiview subspace clustering (SDMSC) model that performs joint deep feature embedding and subspace analysis. SDMSC comprehensively explores multiview data and strives to obtain a consensus data affinity relationship agreed by features from not only all views but also all intermediate embedding spaces. With more constraints being cast, the desirable data affinity relationship is supposed to be more reliably recovered. Besides, to secure effective deep feature embedding without label supervision, we propose to use the data affinity relationship obtained with raw features as the supervision signals to self-guide the embedding process. With this strategy, the risk that our deep clustering model being trapped in bad local minima is reduced, bringing us satisfactory clustering results in a higher possibility. The experiments on seven widely used datasets show the proposed method significantly outperforms the state-of-the-art clustering methods. Our code is available at https://github.com/kailigo/dmvsc.git.

Restoring images degraded by rain has attracted more academic attention since rain streaks could reduce the visibility of outdoor scenes. However, most existing deraining methods attempt to remove rain while recovering details in a unified framework, which is an ideal and contradictory target in the image deraining task. Moreover, the relative independence of rain streak features and background features is usually ignored in the feature domain. To tackle these challenges above, we propose an effective Pyramid Feature Decoupling Network (i.e., PFDN) for single image deraining, which could accomplish image deraining and details recovery with the corresponding features. Specifically, the input rainy image features are extracted via a recurrent pyramid module, where the features for the rainy image are divided into two parts, i.e., rain-relevant and rain-irrelevant features. Afterwards, we introduce a novel rain streak removal network for rain-relevant features and remove the rain streak from the rainy image by estimating the rain streak information. Benefiting from lateral outputs, we propose an attention module to enhance the rain-irrelevant features, which could generate spatially accurate and contextually reliable details for image recovery. For better disentanglement, we also enforce multiple causality losses at the pyramid features to encourage the decoupling of rain-relevant and rain-irrelevant features from the high to shallow layers. Extensive experiments demonstrate that our module can well model the rain-relevant information over the domain of the feature. Our framework empowered by PFDN modules significantly outperforms the state-of-the-art methods on single image deraining with multiple widely-used benchmarks, and also shows superiority in the fully-supervised domain.

One of the key tasks for an intelligent visual surveillance system is to automatically re-identify objects of interest, e.g., persons or vehicles, from nonoverlapping camera views. This demand incurs the vast investigation of person re-identification (re-ID) and vehicle re-ID techniques, especially those deep learning-based ones. While most recent algorithms focus on designing new convolutional neural networks, less attention is paid to the loss functions, which are of vital roles as well. Triplet loss and softmax loss are the two losses that are extensively used, both of which, however, have limitations. Triplet loss optimizes the model to produce features with which samples from the same class have higher similarity than those from different classes. The problem of triplet loss is that the number of triplets to be constructed grows cubically with training samples, which causes scalability issue, unstable performance, and slow convergence. Softmax loss has favorable scalable property and is widely used for large-scale classification problems. However, since Softmax loss only aims to separate well training classes, its performance for re-ID tasks is not desirable because the model is tested to measure the similarity of samples from unseen classes. We propose the support neighbor (SN) loss, which avoids the limitations of the abovementioned two losses. Unlike triplet loss that is calculated based on triplets, SN loss is derived from K -nearest neighbors (SNs) of anchor samples. The SNs of an anchor are unique, containing more valuable contextual information and neighborhood structure of the anchor, and thus contribute to more stable performance and reliable embedding from image space to feature space. Based on the SNs, a softmax-like separation term and a squeeze term are proposed, which encourage interclass separation and intraclass compactness, respectively. Experiments show that SN loss surpasses triplet and softmax losses with the same backbone network and reaches the state-of-the-art performance for both person and vehicle re-ID using a ResNet50 backbone when combined with training tricks.

The extraction of auto-correlation in images has shown great potential in deep learning networks, such as the self-attention mechanism in the channel domain and the self-similarity mechanism in the spatial domain. However, the realization of the above mechanisms mostly requires complicated module stacking and a large number of convolution calculations, which inevitably increases model complexity and memory cost. Therefore, we propose a pseudo 3D auto-correlation network (P3AN) to explore a more efficient way of capturing contextual information in image de-noising. On the one hand, P3AN uses fast 1D convolution instead of dense connections to realize criss-cross interaction, which requires less computational resources. On the other hand, the operation does not change the feature size and makes it easy to expand. It means that only a simple adaptive fusion is needed to obtain contextual information that includes both the channel domain and the spatial domain. Our method built a pseudo 3D auto-correlation attention block through 1D convolutions and a lightweight 2D structure for more discriminative features. Extensive experiments have been conducted on three synthetic and four real noisy datasets. According to quantitative metrics and visual quality evaluation, the P3AN shows great superiority and surpasses state-of-the-art image denoising methods.

High-quality high-resolution (HR) magnetic resonance (MR) images afford more detailed information for reliable diagnosis and quantitative image analyses. Deep convolutional neural networks (CNNs) have shown promising ability for MR image super-resolution (SR) given low-resolution (LR) MR images. The LR MR images usually share some visual characteristics: repeating patterns, relatively simpler structures, and less informative background. Most previous CNN-based SR methods treat the spatial pixels (including the background) equally. They also fail to sense the entire space of the input, which is critical for high-quality MR image SR. To address those problems, we propose squeeze and excitation reasoning attention networks (SERAN) for accurate MR image SR. We propose to squeeze attention from global spatial information of the input and obtain global descriptors. Such global descriptors enhance the network’s ability to focus on more informative regions and structures in MR images. We further build relationship among those global descriptors and propose primitive relationship reasoning attention. The global descriptors are further refined with learned attention. To fully make use of the aggregated information, we adaptively recalibrate feature responses with learned adaptive attention vectors. These attention vectors select a subset of global descriptors to complement each spatial location for accurate details and texture reconstruction. We propose squeeze and excitation attention with residual scaling, which not only stabilizes the training but also makes it flexible to other basic networks. Extensive experiments show the effectiveness of our proposed SERAN, which clearly surpasses state-of-the-art methods on benchmarks quantitatively and visually.

This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the help of labeled samples from a source domain. Several SSDA methods have been proposed recently, which however fail to fully exploit the value of the few labeled target samples. In this paper, we propose Enhanced Categorical Alignment and Consistency Learning (ECACL), a holistic SSDA framework that incorporates multiple mutually complementary domain alignment techniques. ECACL includes two categorical domain alignment techniques that achieve class-level alignment, a strong data augmentation based technique that enhances the model’s generalizability and a consistency learning based technique that forces the model to be robust with image perturbations. These techniques are applied on one or multiple of the three inputs (labeled source, unlabeled target, and labeled target) and align the domains from different perspectives. ECACL unifies them together and achieves fairly comprehensive domain alignments that are much better than the existing methods: For example, ECACL raises the state-of-the-art accuracy from 68.4 to 81.1 on VisDA2017 and from 45.5 to 53.4 on DomainNet for the 1-shot setting. Our code is available at https://github.com/kailigo/pacl.

Deep convolutional neural networks (CNNs) have pushed forward the frontier of super-resolution (SR) research. However, current CNN models exhibit a major flaw: they are biased towards learning low-frequency signals. This bias becomes more problematic for the image SR task which targets reconstructing all fine details and image textures. To tackle this challenge, we propose to improve the learning of high-frequency features both locally and globally and introduce two novel architectural units to existing SR models. Specifically, we propose a dynamic highpass filtering (HPF) module that locally applies adaptive filter weights for each spatial location and channel group to preserve high-frequency signals. We also propose a matrix multi-spectral channel attention (MMCA) module that predicts the attention map of features decomposed in the frequency domain. This module operates in a global context to adaptively recalibrate feature responses at different frequencies. Extensive qualitative and quantitative results demonstrate that our proposed modules achieve better accuracy and visual improvements against state-of-the-art methods on several benchmark datasets.

Deep convolutional neural networks (CNNs) are achieving great successes for image super-resolution (SR), where global context is crucial for accurate restoration. However, the basic convolutional layer in CNNs is designed to extract local patterns, lacking the ability to model global context. With global context information, lots of efforts have been devoted to augmenting SR networks, especially by global feature interaction methods. These works incorporate the global context into local feature representation. However, recent advances in neuroscience show that it is necessary for the neurons to dynamically modulate their functions according to context, which is neglected in most CNN based SR methods. Motivated by those observations and analyses, we propose context reasoning attention network (CRAN) to modulate the convolution kernel according to the global context adaptively. Specifically, we extract global context descriptors, which are further enhanced with semantic reasoning. Channel and spatial interactions are then introduced to generate context reasoning attention mask, which is applied to modify the convolution kernel adaptively. Such a modulated convolution layer is utilized as basic component to build the blocks and networks. Extensive experiments on benchmark datasets with multiple degradation models show that CRAN obtains superior results and favorable trade-off between performance and model complexity.

For magnetic resonance (MR) images sharing visual characteristics, the internal structure repetitions of different scales are considerable image-specific priors. Following the traditional algorithms, we try to combine external dataset-driven learning with the internal self-similarity for MR image super-resolution (SR). We propose a pyramid orthogonal attention network (POAN) based on dual self-similarity. On the one hand, by combining the point-similarity and the pyramid-similarity, sufficient spatial autocorrelation is explored to alleviate less training data limitation. On the other hand, the non-reduction channel attention mechanism maximizes inter-channel dependence. It increases the probability of the high-frequency region (e.g., structural textures and edges) being activated while suppresses low-frequency regions (e.g., background) adaptively. Out proposed POAN reconstructs the MR image under the guidance of pyramid orthogonal attention. Extensive experiments demonstrate that our method obtains the best results compared with state-of-the-art MR image SR methods quantitatively and visually.

The feedback mechanism in the human visual system extracts high-level semantics from noisy scenes. It then guides low-level noise removal, which has not been fully explored in image denoising networks based on deep learning. The commonly used fully-supervised network optimizes parameters through paired training data. However, unpaired images without noise-free labels are ubiquitous in the real world. Therefore, we proposed a multi-scale selective feedback network (MSFN) with the dual loss. We allow shallow layers to access valuable contextual information from the following deep layers selectively between two adjacent time steps. Iterative refinement mechanism can remove complex noise from coarse to fine. The dual regression is designed to reconstruct noisy images to establish closed-loop supervision that is training-friendly for unpaired data. We use the dual loss to optimize the primary clean-to-noisy task and the dual noisy-to-clean task simultaneously. Extensive experiments prove that our method achieves state-of-the-art results and shows better adaptability on real-world images than the existing methods.

Existing deep learning real denoising methods require a large amount of noisy-clean image pairs for supervision. Nonetheless, capturing a real noisy-clean dataset is an unacceptable expensive and cumbersome procedure. To alleviate this problem, this work investigates how to generate realistic noisy images. Firstly, we formulate a simple yet reasonable noise model that treats each real noisy pixel as a random variable. This model splits the noisy image generation problem into two sub-problems: image domain alignment and noise domain alignment. Subsequently, we propose a novel framework, namely Pixel-level Noise-aware Generative Adversarial Network (PNGAN). PNGAN employs a pre-trained real denoiser to map the fake and real noisy images into a nearly noise-free solution space to perform image domain alignment. Simultaneously, PNGAN establishes a pixel-level adversarial training to conduct noise domain alignment. Additionally, for better noise fitting, we present an efficient architecture Simple Multi-scale Network (SMNet) as the generator. Qualitative validation shows that noise generated by PNGAN is highly similar to real noise in terms of intensity and distribution. Quantitative experiments demonstrate that a series of denoisers trained with the generated noisy images achieve state-of-the-art (SOTA) results on four real denoising benchmarks.

Graph Similarity Computation (GSC) is essential to wide-ranging graph applications such as retrieval, plagiarism/anomaly detection, etc. The exact computation of graph similarity, e.g., Graph Edit Distance (GED), is an NP-hard problem that cannot be exactly solved within an adequate time given large graphs. Thanks to the strong representation power of graph neural network (GNN), a variety of GNN-based inexact methods emerged. To capture the subtle difference across graphs, the key success is designing the dense interaction with features fusion at the early stage, which, however, is a trade-off between speed and accuracy. For slow learning of graph similarity, this paper proposes a novel early-fusion approach by designing a co-attention-based feature fusion network on multilevel GNN features. To further improve the speed without much accuracy drop, we introduce an efficient GSC solution by distilling the knowledge from the slow early-fusion model to the student one for fast inference. Such a student model also enables the offline collection of individual graph embeddings, speeding up the inference time in orders. To address the instability through knowledge transfer, we decompose the dynamic joint embedding into the static pseudo individual ones for precise teacher-student alignment. The experimental analysis on the real-world datasets demonstrates the superiority of our approach over the state-of-the-art methods on both accuracy and efficiency. Particularly, we speed up the prior art by more than 10x on the benchmark AIDS data.

Lightweight image super-resolution (SR) networks have obtained promising results with moderate model size. Many SR methods have focused on designing lightweight architectures, which neglect to further reduce the redundancy of network parameters. On the other hand, model compression techniques, like neural architecture search and knowledge distillation, typically consume considerable memory and computation resources. In contrast, network pruning is a cheap and effective model compression technique. However, it is hard to be applied to SR networks directly, because filter pruning for residual blocks is well-known tricky. To address the above issues, we propose aligned structured sparsity learning (ASSL), which introduces a weight normalization layer and applies $L_2$ regularization to the scale parameters for sparsity. To align the pruned locations across different layers, we propose a \emph{sparsity structure alignment} penalty term, which minimizes the norm of soft mask gram matrix. We apply aligned structured sparsity learning strategy to train efficient image SR network, named as ASSLN, with smaller model size and lower computation than state-of-the-art methods. We conduct extensive comparisons with lightweight SR networks. Our ASSLN achieves superior performance gains over recent methods quantitatively and visually.

Recently, deep convolutional neural network (CNN) has achieved great success for image restoration (IR) and provided hierarchical features at the same time. However, most deep CNN based IR models do not make full use of the hierarchical features from the original low-quality images; thereby, resulting in relatively-low performance. In this work, we propose a novel and efficient residual dense network (RDN) to address this problem in IR, by making a better tradeoff between efficiency and effectiveness in exploiting the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via densely connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory mechanism. To adaptively learn more effective features from preceding and current local features and stabilize the training of wider network, we proposed local feature fusion in RDB. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. We demonstrate the effectiveness of RDN with several representative IR applications, single image super-resolution, Gaussian image denoising, image compression artifact reduction, and image deblurring. Experiments on benchmark and real-world datasets show that our RDN achieves favorable performance against state-of-the-art methods for each IR task quantitatively and visually.

Image denoising is a classical topic yet still a challenging problem, especially for reducing noise from the texture information. Feature scaling (e.g., downscale and upscale) is a widely practice in image denoising to enlarge receptive field size and save resources. However, such a common operation would lose some visual informative details. To address those problems, we propose fast and accurate image denoising via attention guided scaling (AGS). We find that the main informative feature channel and visual primitives during the scaling should keep similar. We then propose to extract the global channel-wise attention to maintain main channel information. Moreover, we propose to collect global descriptors by considering the entire spatial feature. And we then distribute the global descriptors to local positions of the scaled feature, based on their specific needs. We further introduce AGS for adversarial training, resulting in a more powerful discriminator. Extensive experiments show the effectiveness of our proposed method, where we clearly surpass all the state-of-the-art methods on most popular synthetic and real-world denoising benchmarks quantitatively and visually. We further show that our network contributes to other high-level vision applications and improves their performances significantly.

The state-of-the-art multitask multiview (MTMV) learning tackles a scenario where multiple tasks are related to each other via multiple shared feature views. However, in many real-world scenarios where a sequence of the multiview task comes, the higher storage requirement and computational cost of retraining previous tasks with MTMV models have presented a formidable challenge for this lifelong learning scenario. To address this challenge, in this article, we propose a new continual multiview task learning model that integrates deep matrix factorization and sparse subspace learning in a unified framework, which is termed deep continual multiview task learning (DCMvTL). More specifically, as a new multiview task arrives, DCMvTL first adopts a deep matrix factorization technique to capture hidden and hierarchical representations for this new coming multiview task while accumulating the fresh multiview knowledge in a layerwise manner. Then, a sparse subspace learning model is employed for the extracted factors at each layer and further reveals cross-view correlations via a self-expressive constraint. For model optimization, we derive a general multiview learning formulation when a new multiview task comes and apply an alternating minimization strategy to achieve lifelong learning. Extensive experiments on benchmark data sets demonstrate the effectiveness of our proposed DCMvTL model compared with the existing state-of-the-art MTMV and lifelong multiview task learning models.

Super-resolution (SR) and landmark localization of tiny faces are highly correlated tasks. On the one hand, landmark localization could obtain higher accuracy with faces of high-resolution (HR). On the other hand, face SR would benefit from prior knowledge of facial attributes such as landmarks. Thus, we propose a joint alignment and SR network to simultaneously detect facial landmarks and super-resolve tiny faces. More specifically, a shared deep encoder is applied to extract features for both tasks by leveraging complementary information. To exploit representative power of the hierarchical encoder, intermediate layers of a shared feature extraction module are fused to form efficient feature representations. The fused features are then fed to task-specific modules to detect landmarks and super-resolve face images in parallel. Extensive experiments demonstrate that the proposed model significantly outperforms the state-of-the-art in both landmark localization and SR of faces. We show a large improvement for landmark localization of tiny faces (i.e., 16 × 16). Furthermore, the proposed framework yields comparable results for landmark localization on low-resolution (LR) faces (i.e., 64 × 64) to existing methods on HR (i.e., 256 × 256). As for SR, the proposed method recovers sharper edges and more details from LR face images than other state-of-the-art methods, which we demonstrate qualitatively and quantitatively.

The recent flourish of deep learning in various tasks is largely accredited to the rich and accessible labeled data. Nonetheless, massive supervision remains a luxury for many real applications, boosting great interest in label-scarce techniques such as few-shot learning (FSL), which aims to learn concept of new classes with a few labeled samples. A natural approach to FSL is data augmentation and many recent works have proved the feasibility by proposing various data synthesis models. However, these models fail to well secure the discriminability and diversity of the synthesized data and thus often produce undesirable results. In this paper, we propose Adversarial Feature Hallucination Networks (AFHN) which is based on conditional Wasserstein Generative Adversarial networks (cWGAN) and hallucinates diverse and discriminative features conditioned on the few labeled samples. Two novel regularizers, i.e., the classification regularizer and the anti-collapse regularizer, are incorporated into AFHN to encourage discriminability and diversity of the synthesized features, respectively. Ablation study verifies the effectiveness of the proposed cWGAN based feature hallucination framework and the proposed regularizers. Comparative results on three common benchmark datasets substantiate the superiority of AFHN to existing data augmentation based FSL approaches and other state-of-the-art ones.

Video super-resolution (VSR) aims to restore a photo-realistic high-resolution (HR) video frame from both its corresponding low-resolution (LR) frame (reference frame) and multiple neighboring frames (supporting frames). Due to varying motion of cameras or objects, the reference frame and each support frame are not aligned. Therefore, temporal alignment is a challenging yet important problem for VSR. Previous VSR methods usually utilize optical flow between the reference frame and each supporting frame to warp the supporting frame for temporal alignment. However, both inaccurate flow and the image-level warping strategy will lead to artifacts in the warped supporting frames. To overcome the limitation, we propose a temporally-deformable alignment network (TDAN) to adaptively align the reference frame and each supporting frame at the feature level without computing optical flow. The TDAN uses features from both the reference frame and each supporting frame to dynamically predict offsets of sampling convolution kernels. By using the corresponding kernels, TDAN transforms supporting frames to align with the reference frame. To predict the HR video frame, a reconstruction network taking aligned frames and the reference frame is utilized. Experimental results demonstrate that the TDAN is capable of alleviating occlusions and artifacts for temporal alignment and the TDAN-based VSR model outperforms several recent state-of-the-art VSR networks with a comparable or even much smaller model size. The source code and pre-trained models are released in https://github.com/YapengTian/TDAN-VSR.

In this paper, we explore the space-time video super-resolution task, which aims to generate a high-resolution (HR) slow-motion video from a low frame rate (LFR), low-resolution (LR) video. A simple solution is to split it into two sub-tasks: video frame interpolation (VFI) and video super-resolution (VSR). However, temporal interpolation and spatial super-resolution are intra-related in this task. Two-stage methods cannot fully take advantage of the natural property. In addition, state-of-the-art VFI or VSR networks require a large frame-synthesis or reconstruction module for predicting high-quality video frames, which makes the two-stage methods have large model sizes and thus be time-consuming. To overcome the problems, we propose a one-stage space-time video super-resolution framework, which directly synthesizes an HR slow-motion video from an LFR, LR video. Rather than synthesizing missing LR video frames as VFI networks do, we firstly temporally interpolate LR frame features in missing LR video frames capturing local temporal contexts by the proposed feature temporal interpolation network. Then, we propose a deformable ConvLSTM to align and aggregate temporal information simultaneously for better leveraging global temporal contexts. Finally, a deep reconstruction network is adopted to predict HR slow-motion video frames. Extensive experiments on benchmark datasets demonstrate that the proposed method not only achieves better quantitative and qualitative performance but also is more than three times faster than recent two-stage state-of-the-art methods, e.g., DAIN+EDVR and DAIN+RBPN.

Inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our method structurally enforces sparsity constraints upon hidden neurons. The sparsity constraints are favorable for gradient-based learning algorithms and attachable to convolution layers in various networks. Sparsity in neurons enables computation saving by only operating on non-zero components without hurting accuracy. Meanwhile, our method can magnify representation dimensionality and model capacity with negligible additional computation cost. Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks, including image super-resolution, image denoising, and image compression artifacts removal.

Recent advances of person re-identification have well advocated the usage of human body cues to boost performance. However, most existing methods still retain on exploiting a relatively coarse-grained local information. Such information may include redundant backgrounds that are sensitive to the apparently similar persons when facing challenging scenarios like complex poses, inaccurate detection, occlusion and misalignment. In this paper we propose a novel Fine-Grained Spatial Alignment Model (FGSAM) to mine fine-grained local information to handle the aforementioned challenge effectively. In particular, we first design a pose resolve net with channel parse blocks (CPB) to extract pose information in pixel-level. This network allows the proposed model to be robust to complex pose variations while suppressing the redundant backgrounds caused by inaccurate detection and occlusion. Given the extracted pose information, a locally reinforced alignment mode is further proposed to address the misalignment problem between different local parts by considering different local parts along with attribute information in a fine-grained way. Finally, a focal triplet loss is designed to effectively train the entire model, which imposes a constraint on the intra-class and an adaptively weight adjustment mechanism to handle the hard sample problem. Extensive evaluations and analysis on Market1501, DukeMTMC-reid and PETA datasets demonstrate the effectiveness of FGSAM in coping with the problems of misalignment, occlusion and complex poses.

Image-text matching has been a hot research topic bridging the vision and language areas. It remains challenging because the current representation of image usually lacks global semantic concepts as in its corresponding text caption. To address this issue, we propose a simple and interpretable reasoning model to generate visual representation that captures key objects and semantic concepts of a scene. Specifically, we first build up connections between image regions and perform reasoning with Graph Convolutional Networks to generate features with semantic relationships. Then, we propose to use the gate and memory mechanism to perform global semantic reasoning on these relationship-enhanced features, select the discriminative information and gradually generate the representation for the whole scene. Experiments validate that our method achieves a new state-of-the-art for the image-text matching on MS-COCO and Flickr30K datasets. It outperforms the current best method by 6.8% relatively for image retrieval and 4.8% relatively for caption retrieval on MS-COCO (Recall@1 using 1K test set). On Flickr30K, our model improves image retrieval by 12.6% relatively and caption retrieval by 5.8% relatively (Recall@1).

The attention of a deep neural network obtained by back-propagating gradients can effectively explain the decision of the network. They can further be used to explicitly access to the network response to a specific pattern. Considering objects of the same category but from different domains share similar visual patterns, we propose to treat the network attention as a bridge to connect objects across domains. In this paper, we use knowledge from the source domain to guide the network's response to categories shared with the target domain. With weights sharing and domain adversary training, this knowledge can be successfully transferred by regularizing the network's response to the same category in the target domain. Specifically, we transfer the foreground prior from a simple single-label dataset to another complex multi-label dataset, leading to improvement of attention maps. Experiments about the weakly-supervised semantic segmentation task show the effectiveness of our method. Besides, we further explore and validate that the proposed method is able to improve the generalization ability of a classification network in domain adaptation and domain generalization settings.

An assumption widely used in recent neural style transfer methods is that image styles can be described by global statics of deep features like Gram or covariance matrices. Alternative approaches have represented styles by decomposing them into local pixel or neural patches. Despite the recent progress, most existing methods treat the semantic patterns of style image uniformly, resulting unpleasing results on complex styles. In this paper, we introduce a more flexible and general universal style transfer technique: multimodal style transfer (MST). MST explicitly considers the matching of semantic patterns in content and style images. Specifically, the style image features are clustered into sub-style components, which are matched with local content features under a graph cut formulation. A reconstruction network is trained to transfer each sub-style and render the final stylized result. We also generalize MST to improve some existing methods. Extensive experiments demonstrate the superior effectiveness, robustness, and flexibility of MST.

Recently, pose or attribute information has been widely used to solve person re-identification (re-ID) problem. However, the inaccurate output from pose or attribute modules will impair the final person re-ID performance. Since re-ID, pose estimation and attribute recognition are all based on the person appearance information, we propose a Local-refining based Deep Neural Network (LRDNN) to aggregate pose estimation and attribute recognition to improve the re-ID performance. To this end, we add a pose branch to extract the local spatial information and optimize the whole network on both person identity and attribute objectives. To diminish the negative affect from unstable pose estimation, a novel structure called channel parse block (CPB) is introduced to learn weights on different feature channels in pose branch. Then two branches are combined with compact bilinear pooling. Experimental results on Market1501 and DukeMTMC-reid datasets illustrate the effectiveness of the proposed method.

High resolution magnetic resonance (MR) imaging is desirable in many clinical applications due to its contribution to more accurate subsequent analyses and early clinical diagnoses. Single image super-resolution (SISR) is an effective and cost efficient alternative technique to improve the spatial resolution of MR images. In the past few years, SISR methods based on deep learning techniques, especially convolutional neural networks (CNNs), have achieved the state-of-the-art performance on natural images. However, the information is gradually weakened and training becomes increasingly difficult as the network deepens. The problem is more serious for medical images because lacking high quality and effective training samples makes deep models prone to underfitting or overfitting. Nevertheless, many current models treat the hierarchical features on different channels equivalently, which is not helpful for the models to deal with the hierarchical features discriminatively and targetedly. To this end, we present a novel channel splitting network (CSN) to ease the representational burden of deep models. The proposed CSN model divides the hierarchical features into two branches, i.e., residual branch and dense branch, with different information transmissions. The residual branch is able to promote feature reuse, while the dense branch is beneficial to the exploration of new features. Besides, we also adopt the merge-and-run mapping to facilitate information integration between different branches. The extensive experiments on various MR images, including proton density (PD), T1, and T2 images, show that the proposed CSN model achieves superior performance over other state-of-the-art SISR methods.

A class-agnostic tracker typically consists of three key components, i.e., its motion model, its target appearance model, and its updating strategy. However, most recent topperforming trackers mainly focus on constructing complicated appearance models and updating strategies, while using comparatively simple and heuristic motion models that may result in an inefficient search and degrade the tracking performance. To address this issue, we propose a hierarchical tracker that learns to move and track based on the combination of data-driven search at the coarse level, and coarse-to-fine verification at the fine level. At the coarse level, a data-driven motion model learned from deep recurrent reinforcement learning provides our tracker with coarse localization of an object. By formulating motion search as an action-decision problem in reinforcement learning, our tracker utilizes a recurrent convolutional neural network based deep Q-network to effectively learn data-driven searching policies. The learned motion model cannot only significantly reduce the search space, but also provide more reliable interested regions for further verifying. At the fine level, a kernelized correlation filter (KCF) based appearance model is adopted to densely yet efficiently verify a local region centered on the predicted location from the motion model. Through using of circulant matrices and fast Fourier transformation, a large number of candidate samples in the local region can be efficiently and effectively evaluated by the KCF based appearance model. Finally, a simple yet robust estimator is designed to analyze possible tracking failure. The experiments on OTB50 and OTB100 illustrate that our tracker achieves better performance than the state-of-the-art trackers.

Tracking-by-detection is one of the typical paradigms for multi-person tracking, due to the availability of automatic pedestrian detectors. However, existing multi-person trackers are greatly challenged by misalignment in the pedestrian detectors (i.e., excessive background and part missing) and occlusion. To effectively handle these problems, we propose a deep alignment network-based multi-person tracking method with occlusion and motion reasoning. Specifically, the inaccurate detections are first corrected via a deep alignment network, in which an alignment estimation module is used to automatically learn the spatial transformation of these detections. As a result, the deep features from our alignment network will have better representation power and, thus, lead to more consistent tracks. Then, a coarse-to-fine schema is designed for construing a discriminative association cost matrix with spatial, motion, and appearance information. Meanwhile, a principled approach is developed to allow our method to handle occlusion with motion reasoning and the reidentification ability of the pedestrian alignment network. Finally, the association problem is solved via a simple yet real-time Hungarian algorithm. Comprehensive experiments on MOT16, ISSIA soccer, PETS09, and TUD datasets validate the effectiveness and robustness of our proposed tracker.

Most recent learning-based single-image superresolution methods first interpolate the low-resolution (LR) input, from which overlapped LR features are then extracted to reconstruct their high-resolution (HR) counterparts and the final HR image. However, most of them neglect to take advantage of the intermediate recovered HR image to enhance image quality further. We conduct principal component analysis (PCA) to reduce LR feature dimension. Then we find that the number of principal components after conducting PCA in the LR feature space from the reconstructed images is larger than that from the interpolated images by using bicubic interpolation. Based on this observation, we present an unsophisticated yet effective framework named collaborative representation cascade (CRC) that learns multilayer mapping models between LR and HR feature pairs. In particular, we extract the features from the intermediate recovered image to upscale and enhance LR input progressively. In the learning phase, for each cascade layer, we use the intermediate recovered results and their original HR counterparts to learn single-layer mapping model. Then, we use this single-layer mapping model to super-resolve the original LR inputs. And the intermediate HR outputs are regarded as training inputs for the next cascade layer, until we obtain multilayer mapping models. In the reconstruction phase, we extract multiple sets of LR features from the LR image and intermediate recovered. Then, in each cascade layer, mapping model is utilized to pursue HR image. Our experiments on several commonly used image SR testing datasets show that our proposed CRC method achieves state-of-the-art image SR results.

A very deep convolutional neural network (CNN) has recently achieved great success for image super-resolution (SR) and offered hierarchical features as well. However, most deep CNN based SR models do not make full use of the hierarchical features from the original low-resolution (LR) images, thereby achieving relatively-low performance. In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via dense connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory (CM) mechanism. Local feature fusion in RDB is then used to adaptively learn more effective features from preceding and current local features and stabilizes the training of wider network. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. Experiments on benchmark datasets with different degradation models show that our RDN achieves favorable performance against state-of-the-art methods.

Person re-identification (re-ID) has recently been tremendously boosted due to the advancement of deep convolutional neural networks (CNN). The majority of deep re-ID methods focus on designing new CNN architectures, while less attention is paid on investigating the loss functions. Verification loss and identification loss are two types of losses widely used to train various deep re-ID models, both of which however have limitations. Verification loss guides the networks to generate feature embeddings of which the intra-class variance is decreased while the inter-class ones is enlarged. However, training networks with verification loss tends to be of slow convergence and unstable performance when the number of training samples is large. On the other hand, identification loss has good separating and scalable property. But its neglect to explicitly reduce the intra-class variance limits its performance on re-ID, because the same person may have significant appearance disparity across different camera views. To avoid the limitations of the two types of losses, we propose a new loss, called support neighbor (SN) loss. Rather than being derived from data sample pairs or triplets, SN loss is calculated based on the positive and negative support neighbor sets of each anchor sample, which contain more valuable contextual information and neighborhood structure that are beneficial for more stable performance. To ensure scalability and separability, a softmax-like function is formulated to push apart the positive and negative support sets. To reduce intra-class variance, the distance between the anchor's nearest positive neighbor and furthest positive sample is penalized. Integrating SN loss on top of Resnet50, superior re-ID results to the state-of-the-art ones are obtained on several widely used datasets.

Most state-of-the-art results on image classification tasks were obtained by residual neural networks, which use stochastic gradient descent (SGD) with momentum for training. In most cases, the learning rate drops by a constant factor every pre-defined number of epochs. However, it is difficult and time-consuming to estimate how many epochs to drop the learning rate. To tackle this problem, cyclical learning rate is gaining popularity in gradient-based optimization to improve the convergence speed in accelerated gradient schemes. But cyclical learning rate scheme scans a broad range of learning rate, some of which are not suitable for deep neural network training. In this paper, we propose a simple yet effective exponential decay sine wave like learning rate technique for SGD to improve its convergence speed. In the training process, the learning rate would vary in sine wave way. While the maximum value of sine wave would decay exponentially along with training epochs. An ensemble of wide residual nets with our proposed learning scheme achieves 3.01% and 16.03% errors on CIFAR-10 and CIFAR-100 respectively. Furthermore, our proposed method uses far less number of epochs than most recent learning rate strategies, accelerating neural network training tremendously.

We propose a novel single image super-resolution (SR) algorithm based on the projective dictionary pair learning with anchored neighborhood regression. Different from previous dictionary learning methods that aim to learn only a synthesis or an analysis dictionary, our method would learn both types of dictionaries jointly for regression to achieve image SR. We first cluster the training features into K clusters in order to learn synthesis and analysis dictionaries. Moreover, we learn the regressions with the training samples at training phase and use them on reconstruction stage. As shown in our experimental results, the proposed method obtains high-quality SR results quantitatively and visually against state-of-the-art methods.

There is an increasing need for high-quality multimedia applications based on block-based hybrid video coding. Inevitably, the frame will degrade during the process of block-wise intra/inter prediction, transformation, and quantization, especially when the bit rate is low. In this paper, we propose an efficient decompressed video enhancement algorithm based on the adjusted anchored neighborhood regression (A+) method. In our work, first, we learn offline linear regressors, i.e. projection matrices from the decompressed to original video frames in the training phase. For grouping anchored neighborhoods more accurately, we adopt MI-KSVD rather than KSVD to learn the dictionary. Moreover, we exploit the mutual coherence between dictionary atoms and training samples to find the nearest neighbors. Second, in the enhancement phase, we boost the quality of input decompressed videos offline by learned regression priors. To verify the robustness of our enhancement method, extensive experiments are conducted. As shown in our experimental results, the proposed enhancement method yields superior performance both objectively and subjectively.

Clustering and collaborative representation (CCR) have recently been used in fast single image super-resolution (SR). In this paper, we propose an effective and fast single image super-resolution (SR) algorithm by combining clustering and collaborative representation. In particular, we first cluster the feature space of low-resolution (LR) images into multiple LR feature subspaces and group the corresponding high-resolution (HR) feature subspaces. The local geometry property learned from the clustering process is used to collect numerous neighbor LR and HR feature subsets from the whole feature spaces for each cluster center. Multiple projection matrices are then computed via collaborative representation to map LR feature subspaces to HR subspaces. For an arbitrary input LR feature, the desired HR output can be estimated according to the projection matrix, whose corresponding LR cluster center is nearest to the input. Moreover, by learning statistical priors from the clustering process, our clustering-based SR algorithm would further decrease the computational time in the reconstruction phase. Extensive experimental results on commonly used datasets indicate that our proposed SR algorithm obtains compelling SR images quantitatively and qualitatively against many state-of-the-art methods.

In this paper, we employ unified mutual coherence between the dictionary atoms and atoms/samples when learning the dictionary and sampling anchored neighborhoods respectively for image super-resolution (SR) application algorithm. On one hand, an incoherence promoting term in dictionary learning for SR is introduced to encourage dictionary atoms, associated to different anchored regressors, to be as independent as possible, while still allowing for different regressors to share same samples. On the other hand, a unified form with mutual coherence between dictionary atoms and training samples is proposed when we group neighborhoods of samples centered on each atom and find the nearest neighbors for input samples in image super-resolution. Extensive experimental results on commonly used datasets demonstrate that our method outperforms state-of-the-art methods by obtaining compelling results with improved quality, such as sharper edges, finer textures and higher structural similarity.

We propose a fast single image super-resolution algorithm based on adaptive local nonparametric regression. Making use of dictionary learning and regression, we learn multiple projection matrices mapping low-resolution features to their corresponding high-resolution ones directly. Different from previous linear regression that needs some constant parameters, our method would not use extra parameters for regression. We use the mutual coherence between dictionary atom and low-resolution feature as a label to reconstruct more sophisticated high-resolution feature. As we use the same form of mutual coherence as labels in both training and testing phases, our method would lead to an adaptive local linear regression model. Moreover, we investigate the statistical property of the dictionary atoms from the training features. Utilizing the learned statistical priors, our method would not only obtain more useful dictionary atoms, but also further decrease the computational time. As shown in our experimental results, the proposed method yields high-quality super-resolution images quantitatively and visually against state-of-the-art methods.