Nonlinear activation plays an essential role in neural networks (NNs) for their generalization ability. However, implementing intricate mathematical operations on hardware platforms, including Field-Programmable Gate Arrays (FPGAs), presents significant challenges. Prior works based on piecewise functions or look-up table (LUT) have encountered difficulties in balancing precision requirements with fair hardware overhead and often necessitating complex manual interventions. To address these issues, this paper proposes DIF-LUT Pro, an automated tool for simple yet scalable approximation for various nonlinear activations on FPGA. Specifically, the proposed algorithm achieves self-adaptive hardware design oriented towards target precision, by piecewise linear matching to fit the function derivative roughly and range addressable LUT to offset the difference. Moreover, DIF-LUT Pro integrates the algorithm into an automated tool, allowing users to configure the customized interface and generate the corresponding hardware description language (HDL) code with a single click. Experimental results show that (1) DIF-LUT Pro features robust automation and fair generality, capable of generating equitable hardware designs under various user configurations across different FPGA platforms; (2) DIF-LUT Pro produces approximations that are simple yet effective, achieving competitive performance compared to previous expert-crafted designs. Furthermore, two detailed case studies demonstrate the efficient application of DIF-LUT Pro on NeRF and SEResnet, proving its practical value. Our source code is open-source and available at https://github.com/AdrianLiu00/DIF-LUT-Tool.

Cross-domain talking head generation, such as animating a static cartoon animal photo with real human video, is crucial for personalized content creation. However, prior works typically rely on domain-specific frameworks and paired videos, limiting its utility and complicating its architecture with additional motion alignment modules. Addressing these shortcomings, we propose Anytalk, a unified framework that eliminates the need for paired data and learns a shared motion representation across different domains. The motion is represented by canonical 3D keypoints extracted using an unsupervised 3D keypoint detector. Further, we propose an expression consistency loss to improve the accuracy of facial dynamics in video generation. Additionally, we present AniTalk, a comprehensive dataset designed for advanced multi-modal cross-domain generation. Our experiments demonstrate that Anytalk excels at generating high-quality, multi-modal talking head videos, showcasing remarkable generalization capabilities across diverse domains.

The rapid evolution of artificial intelligence in drug discovery encounters challenges with generalization and extensive training, yet Large Language Models (LLMs) offer promise in reshaping interactions with complex molecular data. Our novel contribution, InstructMol, a multi-modal LLM, effectively aligns molecular structures with natural language via an instruction-tuning approach, utilizing a two-stage training strategy that adeptly combines limited domain-specific data with molecular and textual information. InstructMol showcases substantial performance improvements in drug discovery-related molecular tasks, surpassing leading LLMs and significantly reducing the gap with specialists, thereby establishing a robust foundation for a versatile and dependable drug discovery assistant.

Reconstructing animatable and high-quality 3D head avatars from monocular videos, especially with realistic relighting, is a valuable task. However, the limited information from single-view input, combined with the complex head poses and facial movements, makes this challenging. Previous methods achieve real-time performance by combining 3D Gaussian Splatting with a parametric head model, but the resulting head quality suffers from inaccurate face tracking and limited expressiveness of the deformation model. These methods also fail to produce realistic effects under novel lighting conditions. To address these issues, we propose HRAvatar, a 3DGS-based method that reconstructs high-fidelity, relightable 3D head avatars. HRA-vatar reduces tracking errors through end-to-end optimization and better captures individual facial deformations using learnable blendshapes and learnable linear blend skinning. Additionally, it decomposes head appearance into several physical properties and incorporates physically-based shading to account for environmental lighting. Extensive experiments demonstrate that HRAvatar not only reconstructs superior-quality heads but also achieves realistic visual effects under varying lighting conditions. Video results and code are available at the project page.

This paper introduces FAMERS, a tile-based hardware accelerator designed for efficient 3D Gaussian Splatting (3DGS) inference on edge-deployed Field Programmable Gate Arrays (FPGAs). 3DGS has emerged as a powerful technique for photorealistic image rendering, leveraging anisotropic Gaussians to balance computational efficiency and visual fidelity. However, the high memory and processing demands of 3DGS pose significant challenges for real-time applications on resource-constrained edge devices. To address these limitations, we present a novel architecture that optimizes both computational and memory overheads through model pruning and compression techniques, enabling high-quality rendering within the constrained memory and processing capabilities of edge platforms. Experimental results demonstrate that our implementation on the Xilinx XC7K325T FPGA achieves a 1.99× speedup and 13.46× energy efficiency compared to NVIDIA RTX 3060M Laptop GPU, underscoring the viability of our approach for real-time applications in virtual and augmented reality.

Due to the vast design space of molecules, generating molecules conditioned on a specific sub-structure relevant to a particular function or therapeutic target is a crucial task in computer-aided drug design. Existing works mainly focus on specific tasks, such as linker design or scaffold hopping, each task requires training a model from scratch, and many well-pretrained De Novo molecule generation model parameters are not effectively utilized. To this end, we propose a two-stage training approach, consisting of condition learning and condition optimization. In the condition learning stage, we adopt the idea of ControlNet and design some meaningful adjustments to make the unconditional generative model learn sub-structure conditioned generation. In the condition optimization stage, by using human preference learning, we further enhance the stability and robustness of sub-structure control. In our experiments, only trained on randomly partitioned sub-structure data, the proposed method outperforms previous techniques by generating more valid and diverse molecules. Our method is easy to implement and can be quickly applied to various pre-trained molecule generation models.

Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application potential. 3D human avatar reconstruction typically requires multi-view or monocular videos and training on individual IDs, which is both complex and time-consuming. Furthermore, limited by SMPLX's expressiveness, these methods often focus on body motion but struggle with facial expressions. To address these challenges, we first introduce an expressive human model (EHM) to enhance facial expression capabilities and develop an accurate tracking method. Based on this template model, we propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction. We leverage inverse texture mapping and projection sampling techniques to infer Ubody (upper-body) Gaussians from a single image. The rendered images are refined through a neural refiner. Experimental results demonstrate that GUAVA significantly outperforms previous methods in rendering quality and offers significant speed improvements, with reconstruction times in the sub-second range (0.1s), and supports real-time animation and rendering.

Cascade Ranking is a prevalent architecture in large-scale top-k selection systems like recommendation and advertising platforms. Traditional training methods focus on single-stage optimization, neglecting interactions between stages. Recent advances have introduced interaction-aware training paradigms, but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i.e., end-to-end recall of ground-truth items) and 2) learn effective collaboration patterns for different stages. To address these challenges, we propose LCRON, which introduces a novel surrogate loss function derived from the lower bound probability that ground truth items are selected by cascade ranking, ensuring alignment with the overall objective of the system. According to the properties of the derived bound, we further design an auxiliary loss for each stage to drive the reduction of this bound, leading to a more robust and effective top-k selection. LCRON enables end-to-end training of the entire cascade ranking system as a unified network. Experimental results demonstrate that LCRON achieves significant improvement over existing methods on public benchmarks and industrial applications, addressing key limitations in cascade ranking training and significantly enhancing system performance.

While large language models (LLMs) with Chain-of-Thought (CoT) reasoning excel in mathematics and coding, their potential for systematic reasoning in chemistry, a domain demanding rigorous structural analysis for real-world tasks like drug design and reaction engineering, remains untapped. Current benchmarks focus on simple knowledge retrieval, neglecting step-by-step reasoning required for complex tasks such as molecular optimization and reaction prediction. To address this, we introduce ChemCoTBench, a reasoning framework that bridges molecular structure understanding with arithmetic-inspired operations, including addition, deletion, and substitution, to formalize chemical problem-solving into transparent, step-by-step workflows. By treating molecular transformations as modular "chemical operations", the framework enables slow-thinking reasoning, mirroring the logic of mathematical proofs while grounding solutions in real-world chemical constraints. We evaluate models on two high-impact tasks: Molecular Property Optimization and Chemical Reaction Prediction. These tasks mirror real-world challenges while providing structured evaluability. We further provide ChemCoTDataset, a pioneering 22,000-instance chemical reasoning dataset with expert-annotated chains of thought to facilitate LLM fine-tuning. By providing annotated trainable datasets, a reasoning taxonomy, and baseline evaluations, our work bridges the gap between abstract reasoning methods and practical chemical discovery, establishing a foundation for advancing LLMs as tools for AI-driven scientific innovation.

Most deraining methods work on day scenes while leaving nighttime deraining underexplored, where darkness and non-uniform illuminations pose additional challenges. Consequently, night rain has a quite different appearance varying by location and cannot be effectively handled. To accommodate this issue, we propose a Rain Location Prior (RLP) by implicitly learning it from rainy images to reflect rain location information and boost the performance of deraining models by prior injection. Then, we introduce a Rain Prior Injection Module (RPIM) with a multi-scale scheme to modulate it by attention and emphasize the features of rain streak areas for better injection efficiency. Finally, to alleviate the data scarcity issue and facilitate the research on nighttime deraining, we propose the GTAV-NightRain dataset by considering the interaction between rain streaks and non-uniform illuminations, and provide detailed instructions on data collection pipeline which is highly replicable and flexible to integrate challenging factors of rainy night in the future. Our method outperforms state-of-the-art backbone by 1.3 dB in PSNR and generalizes better on real data such as heavy rain and the presence of glow and glaring lights. Ablation studies are conducted to validate the effectiveness of each component and we visualize RLP to show good interpretability. Moreover, we apply our method to daytime deraining and desnow to show good generalizability on other location-dependent degradations. Our method is a step forward in nighttime deraining and the GTAV-NightRain dataset may become a good complement to previous datasets.

This paper presents Qffusion, a dual-frame-guided framework for portrait video editing. Specifically, we consider a design principle of "animation for editing", and train Qffusion as a general animation framework from two still reference images while we can use it for portrait video editing easily by applying modified start and end frames as references during inference. Leveraging the powerful generative power of Stable Diffusion, we propose a Quadrant-grid Arrangement (QGA) scheme for latent re-arrangement, which arranges the latent codes of two reference images and that of four facial conditions into a four-grid fashion, separately. Then, we fuse features of these two modalities and use self-attention for both appearance and temporal learning, where representations at different times are jointly modeled under QGA. Our Qffusion can achieve stable video editing without additional networks or complex training stages, where only the input format of Stable Diffusion is modified. Further, we propose a Quadrant-grid Propagation (QGP) inference strategy, which enjoys a unique advantage on stable arbitrary-length video generation by processing reference and condition frames recursively. Through extensive experiments, Qffusion consistently outperforms state-of-the-art techniques on portrait video editing.

Rendering photo-realistic novel-view images of complex scenes has been a long-standing challenge in computer graphics. In recent years, great research progress has been made in enhancing rendering quality and accelerating rendering speed in the realm of view synthesis. However, when rendering complex dynamic scenes with sparse views, the rendering quality remains limited due to occlusion problems. Besides, for rendering high-resolution images on dynamic scenes, the rendering speed is still far from real-time. In this work, we propose a generalizable view synthesis method that can render high-resolution novel-view images of complex static and dynamic scenes in real-time from sparse views. To address the occlusion problems arising from the sparsity of input views and the complexity of captured scenes, we introduce an explicit 3D visibility reasoning approach that can efficiently estimate the visibility of sampled 3D points to the input views. The proposed visibility reasoning approach is fully differentiable and can gracefully fit inside the volume rendering pipeline, allowing us to train our networks with only multi-view images as supervision while refining geometry and texture simultaneously. Besides, each module in our pipeline is carefully designed to bypass the time-consuming MLP querying process and enhance the rendering quality of high-resolution images, enabling us to render high-resolution novel-view images in real-time. Experimental results show that our method outperforms previous view synthesis methods in both rendering quality and speed, particularly when dealing with complex dynamic scenes with sparse views.

Blind face restoration under extreme conditions involves reconstructing high-quality face images from severely degraded inputs. These input images are often in poor quality and have extreme facial poses, leading to errors in facial structure and unnatural artifacts within the restored images. In this paper, we show that utilizing 3D priors effectively compensates for structure knowledge deficiencies in 2D priors while preserving the texture details. Based on this, we introduce FREx (Face Restoration under Extreme conditions) that combines structure-accurate 3D priors and texture-rich 2D priors in pretrained generative networks for blind face restoration under extreme conditions. To fuse the different information in 3D and 2D priors, we introduce an adaptive weight module that adjusts the importance of features based on the input image's condition. With this approach, our model can restore structure-accurate and natural-looking faces even when the images have lost a lot of information due to degradation and extreme pose. Extensive experimental results on synthetic and real-world datasets validate the effectiveness of our methods.

Instant-NGP is the state-of-the-art (SOTA) algorithm of Neural Radiance Field (NeRF) and shows great potential to be adopted in ARNR. However, the high cost of memory and computation limits Instant-NGP’s implementation on edge devices. In light of this, we propose a novel FPGA-based accelerator to reduce power consumption, called Booth-NeRF. Booth-NeRF adopts a fully-pipelined technique and is built upon the Booth algorithm. In addition, it introduces a new instruction set to accommodate Multi-Layer Perceptrons (MLPs) of different sizes, ensuring flexibility and efficiency. Moreover, we propose an FPGA-friendly multiplier architecture for matrix multiplication which is capable of performing exact or approximate multiplication using the Booth algorithm and the select-shift-add technique. Evaluations with a Xilinx Kintex XC7K325T board show that Booth-NeRF achieves $2.20\times$ speedup and $1.31\times$ energy efficiency compared with NVIDIA Jetson Xavier NX-16G GPU.

Antibody structure prediction is a critical task in immunological research and therapeutic antibody development. Despite advances in prediction methods, contemporary approaches still face formidable challenges, particularly in accurately modeling Complementarity-determining regions (CDRs). Furthermore, current prediction time costs, typically on the order of minutes, preclude large-scale structure prediction and screening. In this work, we present ImmuFold, a novel deep-learning approach that achieves second-level performance in antibody structure prediction. ImmuFold integrates ImmuBERT, a 650M antibody language model pre-trained on hundreds of millions of natural antibody sequences, with a structure prediction network that directly predicts all-atom structure, encompassing both main chain and side chains. ImmuFold outperforms current methods, including IgFold and AlphaFold2, generating higher-quality antibody structures in approximately one second. Comparative analysis of the antibody binding task demonstrates the superior representational capabilities of ImmuBERT relative to existing language models, a crucial factor underpinning the efficacy of ImmuFold.

Antibodies are proteins produced by the immune system that recognize and bind to specific antigens, and their 3D structures are crucial for understanding their binding mechanism and designing therapeutic interventions. The specificity of antibody-antigen binding predominantly depends on the complementarity-determining regions (CDR) within antibodies.Despite recent advancements in antibody structure prediction, the quality of predicted CDRs remains suboptimal.In this paper, we develop a novel antibody structure refinement method termed FlowAB based on energy-guided flow matching. FlowAB adopts the powerful deep generative method SE(3) flow matching and simultaneously incorporates important physical prior knowledge into the flow model to guide the generation process.The extensive experiments demonstrate that FlowAB can significantly improve the antibody CDR structures. It achieves new state-of-the-art performance on the antibody structure prediction task when used in conjunction with an appropriate prior model while incurring only marginal computational overhead. This advantage makes FlowAB a practical tool in antibody engineering.

We propose DiffSHEG, a Diffusion-based approach for Speech-driven Holistic 3D Expression and Gesture generation with arbitrary length. While previous works focused on co-speech gesture or expression generation individually, the joint generation of synchronized expressions and gestures remains barely explored. To address this, our diffusion-based co-speech motion generation transformer enables uni-directional information flow from expression to gesture, facilitating improved matching of joint expression-gesture distributions. Furthermore, we introduce an outpainting-based sampling strategy for arbitrary long sequence generation in diffusion models, offering flexibility and computational efficiency. Our method provides a practical solution that produces high-quality synchronized expression and gesture generation driven by speech. Evaluated on two public datasets, our approach achieves state-of-the-art performance both quantitatively and qualitatively. Additionally, a user study confirms the superiority of DiffSHEG over prior approaches. By enabling the real-time generation of expressive and synchronized motions, DiffSHEG showcases its potential for various applications in the development of digital humans and embodied agents.

This paper presents a video inversion approach for zero-shot video editing, which models the input video with low-rank representation during the inversion process. The existing video editing methods usually apply the typical 2D DDIM inversion or naï ve spatial-temporal DDIM inversion before editing, which leverages time-varying representation for each frame to derive noisy latent. Unlike most existing approaches, we propose a Spatial-Temporal Expectation-Maximization (STEM) inversion, which formulates the dense video feature under an expectation-maximization manner and iteratively estimates a more compact basis set to represent the whole video. Each frame applies the fixed and global representation for inversion, which is more friendly for temporal consistency during reconstruction and editing. Extensive qualitative and quantitative experiments demonstrate that our STEM inversion can achieve consistent improvement on two state-of-the-art video editing methods. Project page: https://steminv.github.io/page/.

Monocular depth estimation has experienced significant progress on terrestrial images in recent years thanks to deep learning advancements. But it remains inadequate for underwater scenes primarily due to data scarcity. Given the inherent challenges of light attenuation and backscat-ter in water, acquiring clear underwater images or precise depth is notably difficult and costly. To mitigate this issue, learning-based approaches often rely on synthetic data or turn to self- or unsupervised manners. Nonetheless, their performance is often hindered by domain gap and looser constraints. In this paper, we propose a novel pipeline for generating photorealistic underwater images using accurate terrestrial depth. This approach facilitates the supervised training of models for underwater depth estimation, effectively reducing the performance disparity between ter-restrial and underwater environments. Contrary to previous synthetic datasets that merely apply style transfer to terres-trial images without scene content change, our approach uniquely creates vivid non-existent underwater scenes by leveraging terrestrial depth data through the innovative Stable Diffusion model. Specifically, we introduce a specialized Depth2Underwater ControlNet, trained on prepared {Underwater, Depth, Text} data triplets, for this generation task. Our newly developed dataset, Atlantis, enables terres-trial depth estimation models to achieve considerable improvements on unseen underwater scenes, surpassing their terrestrial pretrained counterparts both quantitatively and qualitatively. Moreover, we further show its practical utility by applying the improved depth in underwater image enhancement, and its smaller domain gap from the LLVM perspective. Code and dataset are publicly available at https://github.com/zkawfanx/Atlantis.

Containerization has garnered substantial favor among cloud service providers. Nevertheless, the notable network overhead incurred between containers has prompted concerns within the community. In cloud resource scheduling, collocating service containers that frequently communicate to the same machine - termed “service affinity” - is instrumental in enhancing application performance. In response to this concern, we present a solution that harnesses service affinity and collocates containers to enhance the overall system performance and stability. To maximize the benefits of collocating containers, it is necessary to calculate a new schedule that optimally and efficiently maximizes service affinity, especially within the expansive domain of industry-scale cloud environments. In pursuit of this, we leverage the skewness property of affinity and machine learning to fuse solver-based algorithms, thereby assuring both quality and efficiency for problems at scale. Our methodology encompasses the partitioning of a given task into discrete subproblems, with a keen focus on resolving the most critical ones. Via a graph neural network classifier, we assign each subproblem to be solved independently using methods based on off-the-shelf solvers in our algorithm pool - namely, MIP-based, or column generation. This strategic approach enables the efficient computation of a schedule for a cloud cluster that fully optimizes the overall service affinity. We further propose a heuristic algorithm to compute executable container migration plans for practical use, facilitating the transition to the new placement where service affinity is well optimized. Our solution has been deployed in our large-scale production environment, covering over a million cores within ByteDance. Through the successful real-world production deployment, our approach exhibits an average improvement in end-to-end latency by 23.75% and a reduction in request error rates by 24.09% compared to the original system.

Recent text-to-3D generation methods achieve impressive 3D content creation capacity thanks to the advances in image diffusion models and optimizing strategies. However, current methods struggle to generate correct 3D content for a complex prompt in semantics, i.e., a prompt describing multiple interacted objects binding with different attributes. In this work, we propose a general framework named Progressive3D, which decomposes the entire generation into a series of locally progressive editing steps to create precise 3D content for complex prompts, and we constrain the content change to only occur in regions determined by user-defined region prompts in each editing step. Furthermore, we propose an overlapped semantic component suppression technique to encourage the optimization process to focus more on the semantic differences between prompts. Extensive experiments demonstrate that the proposed Progressive3D framework generates precise 3D content for prompts with complex semantics through progressive editing steps and is general for various text-to-3D methods driven by different 3D representations.

Understanding the 3D structures of protein multimers is crucial, as they play a vital role in regulating various cellular processes. It has been empirically confirmed that the multimer structure prediction (MSP) can be well handled in a step-wise assembly fashion using provided dimer structures and predicted protein-protein interactions (PPIs). However, due to the biological gap in the formation of dimers and larger multimers, directly applying PPI prediction techniques can often cause a poor generalization to the MSP task. To address this challenge, we aim to extend the PPI knowledge to multimers of different scales (i.e., chain numbers). Specifically, we propose PromptMSP, a pre-training and Prompt tuning framework for Multimer Structure Prediction. First, we tailor the source and target tasks for effective PPI knowledge learning and efficient inference, respectively. We design PPI-inspired prompt learning to narrow the gaps of two task formats and generalize the PPI knowledge to multimers of different scales. We provide a meta-learning strategy to learn a reliable initialization of the prompt model, enabling our prompting framework to effectively adapt to limited data for large-scale multimers. Empirically, we achieve both significant accuracy (RMSD and TM-Score) and efficiency improvements compared to advanced MSP models.

The knowledge of protein interactions is crucial but challenging for drug discovery applications. This work focuses on protein interface prediction, which aims to determine whether a pair of residues from different proteins interact. Existing data-driven methods have made significant progress in effectively learning protein structures. Nevertheless, they overlook the conformational changes (i.e., flexibility) within proteins upon binding, leading to poor generalization ability. In this paper, we regard the protein flexibility as an attack on the trained model and aim to defend against it for improved generalization. To fulfill this purpose, we propose ATProt, an adversarial training framework for protein representations to robustly defend against the attack of protein flexibility. ATProt can theoretically guarantee protein representation stability under complicated protein flexibility. Experiments on various benchmarks demonstrate that ATProt consistently improves the performance for protein interface prediction. Moreover, our method demonstrates broad applicability, performing the best even when provided with testing structures from structure prediction models like ESMFold and AlphaFold2.

Molecular representation learning has shown great success in advancing AI-based drug discovery. A key insight of many recent works is that the 3D geometric structure of molecules provides essential information about their physicochemical properties. Recently, denoising diffusion probabilistic models have achieved impressive performance in molecular 3D conformation generation. However, most existing molecular diffusion models treat each atom as an independent entity, overlooking the dependency among atoms within the substructures. This paper introduces a novel approach that enhances molecular representation learning by incorporating substructural information in the diffusion model framework. We propose a novel diffusion model termed SubgDiff for involving the molecular subgraph information in diffusion. Specifically, SubgDiff adopts three vital techniques: i) subgraph prediction, ii) expectation state, and iii) k-step same subgraph diffusion, to enhance the perception of molecular substructure in the denoising network. Experiments on extensive downstream tasks, especially the molecular force predictions, demonstrate the superior performance of our approach.

Language-based colorization produces plausible colors consistent with the language description provided by the user. Recent studies introduce additional annotation to prevent color-object coupling and mismatch issues, but they still have difficulty in distinguishing instances corresponding to the same object words. In this paper, we propose a transformer-based framework to automatically aggregate similar image patches and achieve instance awareness without any additional knowledge. By applying our presented luminance augmentation and counter-color loss to break down the statistical correlation between luminance and color words, our model is driven to synthesize colors with better descriptive consistency. We further collect a dataset to provide distinctive visual characteristics and detailed language descriptions for multiple instances in the same image. Extensive experiments demonstrate our advantages of synthesizing visually pleasing and description-consistent results of instance-aware colorization.

Whole-body mesh recovery aims to estimate the 3D human body, face, and hands parameters from a single image. It is challenging to perform this task with a single network due to resolution issues, i.e., the face and hands are usually located in extremely small regions. Existing works usually detect hands and faces, enlarge their resolution to feed in a specific network to predict the parameter, and finally fuse the results. While this copy-paste pipeline can capture the fine-grained details of the face and hands, the connections between different parts cannot be easily recovered in late fusion, leading to implausible 3D rotation and unnatural pose. In this work, we propose a one-stage pipeline for expressive whole-body mesh recovery, named OSX, without separate networks for each part. Specifically, we design a Component Aware Transformer (CAT) composed of a global body encoder and a local face/hand decoder. The encoder predicts the body parameters and provides a high-quality feature map for the decoder, which performs a feature-level upsample-crop scheme to extract highresolution part-specific features and adopt keypointguided deformable attention to estimate hand and face precisely. The whole pipeline is simple yet effective without any manual post-processing and naturally avoids implausible prediction. Comprehensive experiments demonstrate the effectiveness of OSX. Lastly, we build a large-scale Upper-Body dataset (UBody) with high-quality 2D and 3D whole-body annotations. It contains persons with partially visible bodies in diverse real-life scenarios to bridge the gap between the basic task and downstream applications.

Neural Radiance Field (NeRF) is a state-of-the-art algorithm in the field of novel view synthesis and has the potential to be used in AR/VR. However, the inference of NeRF is time-consuming. Motivated by resource-constraint scenarios on the edge and mixed reality devices, our essential idea is to bridge this gap while improving throughput and power consumption. This paper proposes a high-performance FPGA-based accelerator, with a fully-pipelined design tailored for the vanilla NeRF algorithm. We also design a mechanism to monitor the output of the rendering module to reduce operations. Experimental results show that our accelerator achieves 3.63× energy efficiency over implementation on GPU NVIDIA V100, and 1.31× speed up over state-of-the-art ASIC design if running under the same clock frequency as ASIC.

Audio-driven portrait animation aims to synthesize portrait videos that are conditioned by given audio. Animating high-fidelity and multimodal video portraits has a variety of applications. Previous methods have attempted to capture different motion modes and generate high-fidelity portrait videos by training different models or sampling signals from given videos. However, lacking correlation learning between lip-sync and other movements (e.g., head pose/eye blinking) usually leads to unnatural results. In this paper, we propose a unified system for multi-person, diverse, and high-fidelity talking portrait generation. Our method contains three stages, i.e., 1) Mapping-Once network with Dual Attentions (MODA) generates talking representation from given audio. In MODA, we design a dual-attention module to encode accurate mouth movements and diverse modalities. 2) Facial composer network generates dense and detailed face landmarks, and 3) temporal-guided renderer syntheses stable videos. Extensive evaluations demonstrate that the proposed system produces more natural and realistic video portraits compared to previous methods.

Knowledge Distillation (KD) uses the teacher’s logits as soft labels to guide the student, while self-KD does not need a real teacher to require the soft labels. This work unifies the formulations of the two tasks by decomposing and reorganizing the generic KD loss into a Normalized KD (NKD) loss and customized soft labels for both target class (image’s category) and non-target classes named Universal Self-KD (USKD). We decompose the KD loss and find the non-target loss from it forces the student’s non-target logits to match the teacher’s, but the sum of the two non-target logits is different, preventing them from being identical. NKD normalizes the non-target logits to equalize their sum. It can be generally used for KD and self-KD to better use the soft labels for distillation. USKD generates customized soft labels for both target and non-target classes without a teacher. It smooths the target logit of the student as the soft target label and uses the rank of the intermediate feature to generate the soft non-target labels with Zipf’s law. For KD with teachers, NKD achieves state-of-the-art performance on CIFAR-100 and ImageNet, boosting the ImageNet Top-1 accuracy of Res-18 from 69.90% to 71.96% with a Res-34 teacher. For self-KD without teachers, USKD is the first method that can be effectively applied to both CNN and ViT models with negligible additional time and memory cost, resulting in new state-of-the-art results, such as 1.17% and 0.55% accuracy gains on ImageNet for MobileNet and DeiT-Tiny, respectively. Code is available at https://github.com/yzd-v/cls_KD.

3D GAN inversion aims to achieve high reconstruction fidelity and reasonable 3D geometry simultaneously from a single image input. However, existing 3D GAN inversion methods rely on time-consuming optimization for each individual case. In this work, we introduce a novel encoder-based inversion framework based on EG3D, one of the most widely-used 3D GAN models. We leverage the inherent properties of EG3D’s latent space to design a discriminator and a background depth regularization. This enables us to train a geometry-aware encoder capable of converting the input image into corresponding latent code. Additionally, we explore the feature space of EG3D and develop an adaptive refinement stage that improves the representation ability of features in EG3D to enhance the recovery of fine-grained textural details. Finally, we propose an occlusion-aware fusion operation to prevent distortion in unobserved regions. Our method achieves impressive results comparable to optimization-based methods while operating up to 500 times faster. Our framework is well-suited for applications such as semantic editing.

Accurately reconstructing 3D faces from monocular images and videos is crucial for various applications, such as digital avatar creation. However, the current deep learning-based methods face significant challenges in achieving accurate reconstruction with disentangled facial parameters and ensuring temporal stability in single-frame methods for 3D face tracking on video data. In this paper, we propose TokenFace, a transformer-based monocular 3D face reconstruction model. TokenFace uses separate tokens for different facial components to capture information about different facial parameters and employs temporal transformers to capture temporal information from video data. This design can naturally disentangle different facial components and is flexible to both 2D and 3D training data. Trained on hybrid 2D and 3D data, our model shows its power in accurately reconstructing faces from images and producing stable results for video data. Experimental results on popular benchmarks NoWand Stirling demonstrate that TokenFace achieves state-of-the-art performance, outperforming existing methods on all metrics by a large margin.

Rain can significantly degrade image quality and visibility, making deraining a critical area of research in computer vision. Despite recent progress in learning-based deraining methods, there is a lack of focus on nighttime deraining due to the unique challenges posed by non-uniform local illuminations from artificial light sources. Rain streaks in these scenes have diverse appearances that are tightly related to their relative positions to light sources, making it difficult for existing deraining methods to effectively handle them. In this paper, we highlight the importance of rain streak location information in nighttime deraining. Specifically, we propose a Rain Location Prior (RLP) that is learned implicitly from rainy images using a recurrent residual model. This learned prior contains location information of rain streaks and, when injected into deraining models, can significantly improve their performance. To further improve the effectiveness of the learned prior, we also propose a Rain Prior Injection Module (RPIM) to modulate the prior before injection, increasing the importance of features within rain streak areas. Experimental results demonstrate that our approach outperforms existing state-of-the-art methods by about 1dB and effectively improves the performance of deraining models. We also evaluate our method on real night rainy images to show the capability to handle real scenes with fully synthetic data for training. Our method represents a significant step forward in the area of nighttime deraining and highlights the importance of location information in this challenging problem. The code is publicly available at https://github.com/zkawfanx/RLP.

Recognizing and segmenting actions from long videos is a challenging problem. Most existing methods focus on designing temporal convolutional models. However, these models are limited in their flexibility and ability to model long-term dependencies. Transformers have recently been used in various tasks. But the lack of inductive bias and the inefficiency of handling long video sequences limit the application of Transformers in action segmentation. In this paper, we present a pure Transformer-based model without temporal convolutions in action segmentation, called Temporal U-Transformer. The U-Transformer architecture not only reduces complexity but also introduces an inductive bias that neighboring frames are more likely to belong to the same class. Besides, we further propose a boundary-aware loss based on the distribution of similarity scores between frames from attention modules to improve the ability to recognize boundaries. Extensive experiments show the effectiveness of our method.

Conjugate gradient (CG) is widely used in training sparse neural networks. However, CG, involving a large amount of sparse matrix and vector operations, cannot be efficiently implemented on resource-limited edge devices. In this paper, a high-performance and energy-efficient CG accelerator implemented on edge Field Programmable Gate Array is proposed for fast onsite neural networks training. According to the profiling, we propose a unified matrix multiplier that is compatible with the sparse and dense matrix. We also design a novel T-engine to handle transpose operation with the compressed sparse format. Experimental results show that our proposal outperforms the state-of-the-art FPGA work with a resource reduction of up to 41.3%. In addition, we achieve on average$10.2\times$and$2.0\times$speedup, while$10.1\times$and$3.5\times$better energy efficiency than implementations on CPU and GPU, respectively.

Language-based colorization produces plausible and visually pleasing colors under the guidance of user-friendly natural language descriptions. Previous methods implicitly assume that users provide comprehensive color descriptions for most of the objects in the image, which leads to suboptimal performance. In this paper, we propose a unified model to perform language-based colorization with any-level descriptions. We leverage the pretrained cross-modality generative model for its robust language understanding and rich color priors to handle the inherent ambiguity of any-level descriptions. We further design modules to align with input conditions to preserve local spatial structures and prevent the ghosting effect. With the proposed novel sampling strategy, our model achieves instance-aware colorization in diverse and complex scenarios. Extensive experimental results demonstrate our advantages of effectively handling any-level descriptions and outperforming both language-based and automatic colorization methods. The code and pretrained models are available at: https://github.com/changzheng123/L-CAD.

Existing active learning studies typically work in the closed-set setting by assuming that all data examples to be labeled are drawn from known classes. However, in real annotation tasks, the unlabeled data usually contains a large amount of examples from unknown classes, resulting in the failure of most active learning methods. To tackle this open-set annotation (OSA) problem, we propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation. The LfOSA framework introduces an auxiliary network to model the perexample max activation value (MAV) distribution with a Gaussian Mixture Model, which can dynamically select the examples with highest probability from known classes in the unlabeled set. Moreover, by reducing the temperature T of the loss function, the detection model will be further optimized by exploiting both known and unknown supervision. The experimental results show that the proposed method can significantly improve the selection quality of known classes, and achieve higher classification accuracy with lower annotation cost than state-of-the-art active learning methods. To the best of our knowledge, this is the first work of active learning for open-set annotation.

Recently vision transformer has achieved tremendous success on image-level visual recognition tasks. To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeViT) for video instance segmentation (VIS). Different from previous transformer-based VIS methods, TeViT is nearly convolution-free, which contains a transformer backbone and a query-based video instance segmentation head. In the backbone stage, we propose a nearly parameter-free messenger shift mechanism for early temporal context fusion. In the head stages, we propose a parameter-shared spatiotemporal query interaction mechanism to build the one-to-one correspondence between video instances and queries. Thus, TeViT fully utilizes both frame-level and instance-level temporal context information and obtains strong temporal modeling capacity with negligible extra computational cost. On three widely adopted VIS benchmarks, i.e., YouTube-VIS-2019, YouTube-VIS-2021, and OVIS, TeViT obtains state-of-the-art results and maintains high inference speed, e.g., 46.6 AP with 68.9 FPS on YouTube-VIS-2019. Code is available at https://github.com/hustvl/TeViT.

Action classification has made great progress, but segmenting and recognizing actions from long videos remains a challenging problem. Recently, Transformer-based models with strong sequence modeling ability have succeeded in many se-quence modeling tasks. However, the lack of inductive bias and the difficulty of handling long video sequences limit the application of the Transformer in the action segmentation task. In order to explore the potential of the Transformer in this task, we replace some specific linear layers in the vanilla Transformer with dilated temporal convolution, and a sparse attention mechanism is utilized to reduce the time and space complexities to process long video sequences. Besides, directly using frame-wise classification loss to train the model will cause that frames at boundaries of actions are treated equally with those in the middle of actions, and the learned features are not sensitive to boundaries. We propose a new local log-context attention module to predict whether each frame is at the beginning, middle, or end of an action. Since boundary frames are similar to their neighboring frames of different classes, our similarity-based boundary prediction helps learn more discriminative features. Extensive experiments on three datasets show the effectiveness of our method.

Compositing portrait photographs or videos to novel backgrounds is an important application in computational photography. Seamless blending along boundaries and globally harmonic colors are two desired properties of the photo-realistic composition of foregrounds and new backgrounds. Existing works are dedicated to either foreground alpha matte generation or after-blending harmonization, leading to sub-optimal background replacement when putting foregrounds and backgrounds together. In this work, we unify the two objectives in a single framework to obtain realistic portrait image composites. Specifically, we investigate the usage of a target background and find that a complete background plays a vital role in both seamlessly blending and harmonization. We develop a network to learn the composition process given an imperfect alpha matte with appearance features extracted from the complete background to adjust color distribution. Our dedicated usage of a complete background enables realistic portrait image composition and also temporally stable results on videos. Extensive quantitative and qualitative experiments on both synthetic and real-world data demonstrate that our method achieves state-of-the-art performance.

Reflection is common when we see through a glass window, which not only is a visual disturbance but also influences the performance of computer vision algorithms. Removing the reflection from a single image, however, is highly ill-posed since the color at each pixel needs to be separated into two values belonging to the clear background and the reflection, respectively. To solve this, existing methods use additional priors such as reflection layer smoothness, double reflection effect, and color consistency to distinguish the two layers. However, these low-level priors may not be consistently valid in real cases. In this paper, inspired by the fact that human beings can separate the two layers easily by recognizing the objects and understanding the scene, we propose to use the object semantic cue, which is high-level information, as the guidance to help reflection removal. Based on the data analysis, we develop a multi-task end-to-end deep learning method with a semantic guidance component, to solve reflection removal and semantic segmentation jointly. Extensive experiments on different datasets show significant performance gain when using high-level object-oriented information. We also demonstrate the application of our method to other computer vision tasks.

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, we propose GFP-GAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity. Thanks to the powerful generative facial prior and delicate designs, our GFP-GAN could jointly restore facial details and enhance colors with just a single forward pass, while GAN inversion methods require image-specific optimization at inference. Extensive experiments show that our method achieves superior performance to prior art on both synthetic and real-world datasets.

Single image low light enhancement is an important task and it has many practical applications. Most existing methods adopt a single image approach. Although their performance is satisfying on a static single image, we found, however, they suffer serious temporal instability when handling low light videos. We notice the problem is because existing data-driven methods are trained from single image pairs where no temporal information is available. Unfortunately, training from real temporally consistent data is also problematic because it is impossible to collect pixel-wisely paired low and normal light videos under controlled environments in large scale and diversities with noise of identical statistics. In this paper, we propose a novel method to enforce the temporal stability in low light video enhancement with only static images. The key idea is to learn and infer motion field (optical flow) from a single image and synthesize short range video sequences. Our strategy is general and can extend to large scale datasets directly. Based on this idea, we propose our method which can infer motion prior for single image low light video enhancement and enforce temporal consistency. Rigorous experiments and user study demonstrate the state-of-the-art performance of our proposed method. Our code and model will be publicly available at https://github.com/zkawfanx/StableLLVE.

We present QueryInst, a new perspective for instance segmentation. QueryInst is a multi-stage end-to-end system that treats instances of interest as learnable queries, enabling query based object detectors, e.g., Sparse RCNN, to have strong instance segmentation performance. The attributes of instances such as categories, bounding boxes, instance masks, and instance association embeddings are represented by queries in a unified manner. In QueryInst, a query is shared by both detection and segmentation via dynamic convolutions and driven by parallellysupervised multi-stage learning. We conduct extensive experiments on three challenging benchmarks, i.e., COCO, CityScapes, and YouTube-VIS to evaluate the effectiveness of QueryInst in object detection, instance segmentation, and video instance segmentation tasks. For the first time, we demonstrate that a simple end-to-end query based framework can achieve the state-of-the-art performance in various instance-level recognition tasks. Code is available at https://github.com/hustvl/QueryInst.

Colorization has attracted increasing interest in recent years. Classic reference-based methods usually rely on external color images for plausible results. A large image database or online search engine is inevitably required for retrieving such exemplars. Recent deep-learning-based methods could automatically colorize images at a low cost. However, unsatisfactory artifacts and incoherent colors are always accompanied. In this work, we aim at recovering vivid colors by leveraging the rich and diverse color priors encapsulated in a pretrained Generative Adversarial Networks (GAN). Specifically, we first "retrieve" matched features (similar to exemplars) via a GAN encoder and then incorporate these features into the colorization process with feature modulations. Thanks to the powerful generative color prior and delicate designs, our method could produce vivid colors with a single forward pass. Moreover, it is highly convenient to obtain diverse results by modifying GAN latent codes. Our method also inherits the merit of interpretable controls of GANs and could attain controllable and smooth transitions by walking through GAN latent space. Extensive experiments and user studies demonstrate that our method achieves superior performance than previous works.

Modeling temporal visual context across frames is critical for video instance segmentation (VIS) and other video understanding tasks. In this paper, we propose a fast on-line VIS model termed CrossVIS. For temporal information modeling in VIS, we present a novel crossover learning scheme that uses the instance feature in the current frame to pixel-wisely localize the same instance in other frames. Different from previous schemes, crossover learning does not require any additional network parameters for feature enhancement. By integrating with the instance segmentation loss, crossover learning enables efficient cross-frame instance-to-pixel relation learning and brings cost-free improvement during inference. Besides, a global balanced instance embedding branch is proposed for better and more stable online instance association. We conduct extensive experiments on three challenging VIS benchmarks, i.e., YouTube-VIS-2019, OVIS, and YouTube-VIS-2021 to evaluate our methods. CrossVIS achieves state-of-the-art online VIS performance and shows a decent trade-off between latency and accuracy. Code is available at https://github.com/hustvl/CrossVIS.

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional methods introduce various priors to constrain the solution, yet with limited performance. Meanwhile, the problem is typically solved by supervised learning methods, which is actually not an ideal solution since obtaining ground truth reflectance and shading for massive general natural scenes is challenging and even impossible. In this paper, we propose a novel unsupervised intrinsic image decomposition framework, which relies on neither labeled training data nor hand-crafted priors. Instead, it directly learns the latent feature of reflectance and shading from unsupervised and uncorrelated data. To enable this, we explore the independence between reflectance and shading, the domain invariant content constraint and the physical constraint. Extensive experiments on both synthetic and real image datasets demonstrate consistently superior performance of the proposed method.

Video object detection is a tough task due to the deteriorated quality of video sequences captured under complex environments. Currently, this area is dominated by a series of feature enhancement based methods, which distill beneficial semantic information from multiple frames and generate enhanced features through fusing the distilled information. However, the distillation and fusion operations are usually performed at either frame level or instance level with external guidance using additional information, such as optical flow and feature memory. In this work, we propose a dual semantic fusion network (abbreviated as DSFNet) to fully exploit both frame-level and instance-level semantics in a unified fusion framework without external guidance. Moreover, we introduce a geometric similarity measure into the fusion process to alleviate the influence of information distortion caused by noise. As a result, the proposed DSFNet can generate more robust features through the multi-granularity fusion and avoid being affected by the instability of external guidance. To evaluate the proposed DSFNet, we conduct extensive experiments on the ImageNet VID dataset. Notably, the proposed dual semantic fusion network achieves, to the best of our knowledge, the best performance of 84.1% mAP among the current state-of-the-art video object detectors with ResNet-101 and 85.4% mAP with ResNeXt-101 without using any post-processing steps.

Filtering images is required by numerous multimedia, computer vision and graphics tasks. Despite diverse goals of different tasks, making effective rules is key to the filtering performance. Linear translation-invariant filters with manually designed kernels have been widely used. However, their performance suffers from content-blindness. To mitigate the content-blindness, a family of filters, called joint/guided filters, have attracted a great amount of attention from the community. The main drawback of most joint/guided filters comes from the ignorance of structural inconsistency between the reference and target signals like color, infrared, and depth images captured under different conditions. Simply adopting such guidelines very likely leads to unsatisfactory results. To address the above issues, this paper designs a simple yet effective filter, named mutually guided image filter (muGIF), which jointly preserves mutual structures, avoids misleading from inconsistent structures and smooths flat regions. The proposed muGIF is very flexible, which can work in various modes including dynamic only (self-guided), static/dynamic (reference-guided) and dynamic/dynamic (mutually guided) modes. Although the objective of muGIF is in nature non-convex, by subtly decomposing the objective, we can solve it effectively and efficiently. The advantages of muGIF in effectiveness and flexibility are demonstrated over other state-of-the-art alternatives on a variety of applications. Our code is publicly available at https://sites.google.com/view/xjguo/mugif.

The synchronization between two neural networks by mutual learning can be used to design the neural key exchange protocol. The critical issue is how to evaluate the synchronization without a weight vector. All existing methods have a delay in evaluating the synchronization, which affects the security of the neural key exchange. To evaluate the full synchronization of neural networks more timely and accurately, an improved method for evaluating the synchronization is proposed. First, the frequency that the two networks have the same output in previous steps is used for assessing the degree of them roughly. Second, the hash function is utilized to judge whether the two networks have achieved full synchronization precisely when the degree exceeds a given threshold. The improved method can find the full synchronization between two networks with no information other than the hash value of the weight vector. Compared with other methods, the full synchronization can be detected earlier by two communication partners which adopt the method proposed in this paper. As a result, the successful probability of geometric is reduced. Therefore, the proposed method can enhance the security of the neural exchange protocol.

Convolutional Neural Networks have demonstrated superior performance on single image depth estimation in recent years. These works usually use stacked spatial pooling or strided convolution to get high-level information which are common practices in classification task. However, depth estimation is a dense prediction problem and low-resolution feature maps usually generate blurred depth map which is undesirable in application. In order to produce high quality depth map, say clean and accurate, we propose a network consists of a Dense Feature Extractor (DFE) and a Depth Map Generator (DMG). The DFE combines ResNet and dilated convolutions. It extracts multi-scale information from input image while keeping the feature maps dense. As for DMG, we use attention mechanism to fuse multi-scale features produced in DFE. Our Network is trained end-to-end and does not need any post-processing. Hence, it runs fast and can predict depth map in about 15 fps. Experiment results show that our method is competitive with the state-of-the-art in quantitative evaluation, but can preserve better structural details of the scene depth.

Image filtering is helpful to numerous multimedia, computer vision and graphics tasks. Linear translation-invariant filters with manually designed kernels have been widely used. However, their performance suffers from the content-blindness, say identically treating noises, textures and structures. To mitigate the content-blindness, a family of filters, called joint/guided filters, has attracted much attention from the community, the principle of which is transferring the structure in the reference image to the target one. The main drawback of most joint/guided filters comes from the ignorance of structural inconsistency between the reference and target signals that can be like color, infrared and depth images captured under different conditions. Simply adopting such guidances very likely leads to unsatisfactory results. To address the above issues, this paper designs a simple yet effective filter, named as mutually guided image filter (muGIF), which jointly preserves mutual structures, avoids misleading from inconsistent structures and smooths flat regions. The proposed muGIF is very flexible, which can perform in one of dynamic only (self-guided), static/dynamic and dynamic/dynamic modes. Although the objective of muGIF is in nature non-convex, by subtly decomposing the objective, we can solve it effectively and efficiently. The advantages of muGIF in terms of effectiveness and flexibility are demonstrated over other state-of-the-art alternatives on a variety of applications.

The conflict between range and azimuth ambiguities is a challenging problem for spaceborne high-resolution and wide-swath (HRWS) synthetic aperture radar (SAR) imaging. In this letter, a novel ambiguity resolution approach based on frequency diverse array (FDA) is proposed to retrieve unambiguous signal from that with ambiguities in both range and azimuth domains. By exploiting the range-angle-dependent property of transmit steering vector in FDA and applying the second range dependence compensation approach, echoes from different ambiguous regions are separable in transmit spatial-Doppler frequency domains. Then a corresponding transmit beamformer is designed to extract spectrum component of each ambiguous region, which can be rearranged to comprise the desired unambiguous signal. Compatible with most existing azimuth ambiguity suppression algorithms which employ the receive degrees of freedom, the proposed approach can further enhance the capability of resolving ambiguity for HRWS SAR systems, and its effectiveness is verified by simulation experiments.

Though many tasks in computer vision can be formulated elegantly as pixel-labeling problems, a typical challenge discouraging such a discrete formulation is often due to computational efficiency. Recent studies on fast cost volume filtering based on efficient edge-aware filters provide a fast alternative to solve discrete labeling problems, with the complexity independent of the support window size. However, these methods still have to step through the entire cost volume exhaustively, which makes the solution speed scale linearly with the label space size. When the label space is huge or even infinite, which is often the case for (subpixel-accurate) stereo and optical flow estimation, their computational complexity becomes quickly unacceptable. Developed to search approximate nearest neighbors rapidly, the PatchMatch method can significantly reduce the complexity dependency on the search space size. But, its pixel-wise randomized search and fragmented data access within the 3D cost volume seriously hinder the application of efficient cost slice filtering. This paper presents a generic and fast computational framework for general multi-labeling problems called PatchMatch Filter (PMF). We explore effective and efficient strategies to weave together these two fundamental techniques developed in isolation, i.e., PatchMatch-based randomized search and efficient edge-aware image filtering. By decompositing an image into compact superpixels, we also propose superpixel-based novel search strategies that generalize and improve the original PatchMatch method. Further motivated to improve the regularization strength, we propose a simple yet effective cross-scale consistency constraint, which handles labeling estimation for large low-textured regions more reliably than a single-scale PMF algorithm. Focusing on dense correspondence field estimation in this paper, we demonstrate PMF's applications in stereo and optical flow. Our PMF methods achieve top-tier correspondence accuracy but run much faster than other related competing methods, often giving over 10-100 times speedup.

When one captures images in low-light conditions, the images often suffer from low visibility. Besides degrading the visual aesthetics of images, this poor quality may also significantly degenerate the performance of many computer vision and multimedia algorithms that are primarily designed for high-quality inputs. In this paper, we propose a simple yet effective low-light image enhancement (LIME) method. More concretely, the illumination of each pixel is first estimated individually by finding the maximum value in R, G, and B channels. Furthermore, we refine the initial illumination map by imposing a structure prior on it, as the final illumination map. Having the well-constructed illumination map, the enhancement can be achieved accordingly. Experiments on a number of challenging low-light images are present to reveal the efficacy of our LIME and show its superiority over several state-of-the-arts in terms of enhancement quality and efficiency.

Rain streaks impair visibility of an image and introduce undesirable interference that can severely affect the performance of computer vision and image analysis systems. Rain streak removal algorithms try to recover a rain streak free background scene. In this paper, we address the problem of rain streak removal from a single image by formulating it as a layer decomposition problem, with a rain streak layer superimposed on a background layer containing the true scene content. Existing decomposition methods that address this problem employ either sparse dictionary learning methods or impose a low rank structure on the appearance of the rain streaks. While these methods can improve the overall visibility, their performance can often be unsatisfactory, for they tend to either over-smooth the background images or generate -images that still contain noticeable rain streaks. To address the problems, we propose a method that imposes priors for both the background and rain streak layers. These priors are based on Gaussian mixture models learned on small patches that can accommodate a variety of background appearances as well as the appearance of the rain streaks. Moreover, we introduce a structure residue recovery step to further separate the background residues and improve the decomposition quality. Quantitative evaluation shows our method outperforms existing methods by a large margin. We overview our method and demonstrate its effectiveness over prior work on a number of examples.

This paper addresses the problem of rain streak removal from a single image. Rain streaks impair visibility of an image and introduce undesirable interference that can severely affect the performance of computer vision algorithms. Rain streak removal can be formulated as a layer decomposition problem, with a rain streak layer superimposed on a background layer containing the true scene content. Existing decomposition methods that address this problem employ either dictionary learning methods or impose a low rank structure on the appearance of the rain streaks. While these methods can improve the overall visibility, they tend to leave too many rain streaks in the background image or over-smooth the background image. In this paper, we propose an effective method that uses simple patch-based priors for both the background and rain layers. These priors are based on Gaussian mixture models and can accommodate multiple orientations and scales of the rain streaks. This simple approach removes rain streaks better than the existing methods qualitatively and quantitatively. We overview our method and demonstrate its effectiveness over prior work on a number of examples.

Markov random fields are widely used to model many computer vision problems that can be cast in an energy minimization framework composed of unary and pairwise potentials. While computationally tractable discrete optimizers such as Graph Cuts and belief propagation (BP) exist for multi-label discrete problems, they still face prohibitively high computational challenges when the labels reside in a huge or very densely sampled space. Integrating key ideas from PatchMatch of effective particle propagation and resampling, PatchMatch belief propagation (PMBP) has been demonstrated to have good performance in addressing continuous labeling problems and runs orders of magnitude faster than Particle BP (PBP). However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint. This dependency heavily influences the overall complexity, increasing linearly with the window size. This paper proposes a novel algorithm called sped-up PMBP (SPM-BP) to tackle this critical computational bottleneck and speeds up PMBP by 50-100 times. The crux of SPM-BP is on unifying efficient filter-based cost aggregation and message passing with PatchMatch-based particle generation in a highly effective way. Though simple in its formulation, SPM-BP achieves superior performance for sub-pixel accurate stereo and optical-flow on benchmark datasets when compared with more complex and task-specific approaches.

This paper focuses on dehazing nighttime images. Most existing dehazing methods use models that are formulated to describe haze in daytime. Daytime models assume a single uniform light color attributed to a light source not directly visible in the scene. Nighttime scenes, however, commonly include visible lights sources with varying colors. These light sources also often introduce noticeable amounts of glow that is not present in daytime haze. To address these effects, we introduce a new nighttime haze model that accounts for the varying light sources and their glow. Our model is a linear combination of three terms: the direct transmission, airlight and glow. The glow term represents light from the light sources that is scattered around before reaching the camera. Based on the model, we propose a framework that first reduces the effect of the glow in the image, resulting in a nighttime image that consists of direct transmission and airlight only. We then compute a spatially varying atmospheric light map that encodes light colors locally. This atmospheric map is used to predict the transmission, which we use to obtain our nighttime scene reflection image. We demonstrate the effectiveness of our nighttime haze model and correction method on a number of examples and compare our results with existing daytime and nighttime dehazing methods' results.

This paper addresses extracting two layers from an image where one layer is smoother than the other. This problem arises most notably in intrinsic image decomposition and reflection interference removal. Layer decomposition from a single-image is inherently ill-posed and solutions require additional constraints to be enforced. We introduce a novel strategy that regularizes the gradients of the two layers such that one has a long tail distribution and the other a short tail distribution. While imposing the long tail distribution is a common practice, our introduction of the short tail distribution on the second layer is unique. We formulate our problem in a probabilistic framework and describe an optimization scheme to solve this regularization with only a few iterations. We apply our approach to the intrinsic image and reflection removal problems and demonstrate high quality layer separation on par with other techniques but being significantly faster than prevailing methods.

Nonlocal means (NLM) algorithm has been proven to be an effective context-sensitive denoising approach, where many similar patches spatially far from a given patch could provide nonlocal constraint to the local structure. For hyperspectral image, however, the conventional NLM algorithm becomes inapplicable for the high number of spectral bands. In this letter, we incorporate the image nonlocal self-similarity into the maximum a posteriori estimation for hyperspectral classification. The main novelty lies in the following two aspects: The NLM algorithm is exploited to combine similar local structures and nonlocal averaging; a new class-relativity measurement is proposed to describe the self-similarity in the context of the hyperspectral classification. Several experiments on simulated and real hyperspectral data sets are provided to demonstrate the effectiveness of the proposed algorithm.

This paper introduces an automatic method for removing reflection interference when imaging a scene behind a glass surface. Our approach exploits the subtle changes in the reflection with respect to the background in a small set of images taken at slightly different view points. Key to this idea is the use of SIFT-flow to align the images such that a pixel-wise comparison can be made across the input set. Gradients with variation across the image set are assumed to belong to the reflected scenes while constant gradients are assumed to belong to the desired background scene. By correctly labelling gradients belonging to reflection or background, the background scene can be separated from the reflection interference. Unlike previous approaches that exploit motion, our approach does not make any assumptions regarding the background or reflected scenes' geometry, nor requires the reflection to be static. This makes our approach practical for use in casual imaging scenarios. Our approach is straight forward and produces good results compared with existing methods.