Image restoration (IR) models are typically trained to recover high-quality images using L1 or LPIPS loss. To handle diverse unknown degradations, zero-shot IR methods have also been introduced. However, existing pre-trained and zero-shot IR approaches often fail to align with human preferences, resulting in restored images that may not be favored. This highlights the critical need to enhance restoration quality and adapt flexibly to various image restoration tasks or backbones without requiring model retraining and ideally without labor-intensive preference data collection. In this paper, we propose the first Test-Time Preference Optimization (TTPO) paradigm for image restoration, which enhances perceptual quality, generates preference data on-the-fly, and is compatible with any IR model backbone. Specifically, we design a training-free, three-stage pipeline: (i) generate candidate preference images online using diffusion inversion and denoising based on the initially restored image; (ii) select preferred and dispreferred images using automated preference-aligned metrics or human feedback; and (iii) use the selected preference images as reward signals to guide the diffusion denoising process, optimizing the restored image to better align with human preferences. Extensive experiments across various image restoration tasks and models demonstrate the effectiveness and flexibility of the proposed pipeline.

Recent advancements in 4D generation have demonstrated its remarkable capability in synthesizing photorealistic renderings of dynamic 3D scenes. However, despite achieving impressive visual performance, almost all existing methods overlook the generation of spatial audio aligned with the corresponding 4D scenes, posing a significant limitation to truly immersive audiovisual experiences. To mitigate this issue, we propose Sonic4D, a novel framework that enables spatial audio generation for immersive exploration of 4D scenes. Specifically, our method is composed of three stages: 1) To capture both the dynamic visual content and raw auditory information from a monocular video, we first employ pre-trained expert models to generate the 4D scene and its corresponding monaural audio. 2) Subsequently, to transform the monaural audio into spatial audio, we localize and track the sound sources within the 4D scene, where their 3D spatial coordinates at different timestamps are estimated via a pixel-level visual grounding strategy. 3) Based on the estimated sound source locations, we further synthesize plausible spatial audio that varies across different viewpoints and timestamps using physics-based simulation. Extensive experiments have demonstrated that our proposed method generates realistic spatial audio consistent with the synthesized 4D scene in a training-free manner, significantly enhancing the immersive experience for users.

Image-based virtual try-on (VTON) aims to synthesize photorealistic images of a person wearing specified garments. Despite significant progress, building a universal VTON framework that can flexibly handle diverse and complex tasks remains a major challenge. Recent methods explore multi-task VTON frameworks guided by textual instructions, yet they still face two key limitations: (1) semantic gap between text instructions and reference images, and (2) data scarcity in complex scenarios. To address these challenges, we propose UniFit, a universal VTON framework driven by a Multimodal Large Language Model (MLLM). Specifically, we introduce an MLLM-Guided Semantic Alignment Module (MGSA), which integrates multimodal inputs using an MLLM and a set of learnable queries. By imposing a semantic alignment loss, MGSA captures cross-modal semantic relationships and provides coherent and explicit semantic guidance for the generative process, thereby reducing the semantic gap. Moreover, by devising a two-stage progressive training strategy with a self-synthesis pipeline, UniFit is able to learn complex tasks from limited data. Extensive experiments show that UniFit not only supports a wide range of VTON tasks, including multi-garment and model-to-model try-on, but also achieves state-of-the-art performance.

Text-driven Image to Video Generation (TI2V) aims to generate controllable video given the first frame and corresponding textual description. The primary challenges of this task lie in two parts: (i) how to identify the target objects and ensure the consistency between the movement trajectory and the textual description. (ii) how to improve the subjective quality of generated videos. To tackle the above challenges, we propose a new diffusion-based TI2V framework, termed TIV-Diffusion, via object-centric textual-visual alignment, intending to achieve precise control and high-quality video generation based on textual-described motion for different objects. Concretely, we enable our TIV-Diffuion model to perceive the textual-described objects and their motion trajectory by incorporating the fused textual and visual knowledge through scale-offset modulation. Moreover, to mitigate the problems of object disappearance and misaligned objects and motion, we introduce an object-centric textual-visual alignment module, which reduces the risk of misaligned objects/motion by decoupling the objects in the reference image and aligning textual features with each object individually. Based on the above innovations, our TIV-Diffusion achieves state-of-the-art high-quality video generation compared with existing TI2V methods.

Recent years have witnessed the great success of denoising diffusion samplers in improving the generative capability and sampling efficiency given a pre-trained diffusion model. However, most sampling schedulers in diffusion models lack the sampling dynamics and planning capability for future generation results, leading to suboptimal solutions. To overcome this, we propose the Reinforced Active Sampling Scheduler, termed RaSS, intending to find the optimal sampling trajectory by actively planning and adjusting the sampling steps for each sampling process in time. Concretely, RaSS divides the whole sampling process into five stages and introduces a reinforcement learning (RL) agent to continuously monitor the generated instance and perceive the potential generation results, thereby achieving optimal instance-and state-adaptive sampling steps decision. Meanwhile, a sampling reward is designed to assist the planning capability of the RL agent by balancing the sampling efficiency and generation quality. The RaSS is a plug-and-play module, which is applicable to multiple denoising diffusion samplers of diffusion models. Extensive experiments on different benchmarks have shown that our RaSS can consistently improve the generation quality and efficiency across various tasks, without introducing significant computational overhead.

In this work, we take the first exploration of the recently popular foundation model, *i.e.,* State Space Model/Mamba, in image quality assessment (IQA), aiming at observing and excavating the perception potential in vision Mamba. A series of works on Mamba has shown its significant potential in various fields, *e.g.,* segmentation and classification. However, the perception capability of Mamba remains under-explored. Consequently, we propose QMamba by revisiting and adapting the Mamba model for three crucial IQA tasks, *i.e.,* task-specific, universal, and transferable IQA, which reveals its clear advantages over existing foundational models, *e.g.,* Swin Transformer, ViT, and CNNs, in terms of perception and computational cost. To improve the transferability of QMamba, we propose the StylePrompt tuning paradigm, where lightweight mean and variance prompts are injected to assist task-adaptive transfer learning of pre-trained QMamba for different downstream IQA tasks. Compared with existing prompt tuning strategies, our StylePrompt enables better perceptual transfer with lower computational cost. Extensive experiments on multiple synthetic, authentic IQA datasets, and cross IQA datasets demonstrate the effectiveness of our proposed QMamba.

Multi-modal perception plays a crucial role in preventing deformation and damage during the robotic manipulation of deformable objects. However, integrating new heterogeneous modalities into existing robotic perception frameworks remains a significant challenge, primarily due to the need for massive amounts of paired data. In this paper, we propose Uni-Zipper, a scalable multi-modal fusion framework designed to expand new modalities with the help of semantic enhancement without relying on paired data. Uni-Zipper consists of a tokenizer that projects various modalities into a shared embedding space, a summary word embedding layer with a feature dictionary, a modality alignment space, and dynamic reconfigurable task heads. To facilitate efficient integration and extension of new modalities, the Zipper alignment mechanism is employed, effectively bridging the modality gap between different input types. Our experimental results demonstrate that Uni-Zipper successfully fuses four modalities and enhances performance in downstream tasks. Despite a 12% decrease in parameter count, Uni-Zipper maintains comparable performance.

Recently, AI-generated content (AIGC) has gained significant traction due to its powerful creation capability. However, the storage and transmission of large amounts of high-quality AIGC images inevitably pose new challenges for recent file formats. To overcome this, we define a new file format for AIGC images, named AIGIF, enabling ultra-low bitrate coding of AIGC images. Unlike compressing AIGC images intuitively with pixel-wise space as existing file formats, AIGIF instead compresses the generation syntax. This raises a crucial question: Which generation syntax elements, e.g., text prompt, device configuration, etc, are necessary for compression/transmission? To answer this question, we systematically investigate the effects of three essential factors: platform, generative model, and data configuration. We experimentally find that a well-designed composable bitstream structure incorporating the above three factors can achieve an impressive compression ratio of even up to 1/10,000 while still ensuring high fidelity. We also introduce an expandable syntax in AIGIF to support the extension of the most advanced generation models to be developed in the future.

Video quality assessment tasks rely heavily on the rich features required for video understanding, such as semantic information, texture, and temporal motion. The existing video foundational model, InternVideo2, has demonstrated strong potential in video understanding tasks due to its large parameter size and large-scale multimodal data pertaining. Building on this, we explored the transferability of InternVideo2 to video quality assessment under compression scenarios. To design a lightweight model suitable for this task, we proposed a distillation method to equip the smaller model with rich compression quality priors. Additionally, we examined the performance of different backbones during the distillation process. The results showed that, compared to other methods, our lightweight model distilled from InternVideo2 achieved excellent performance in compression video quality assessment.

Image compression methods are usually optimized isolatedly for human perception or machine analysis tasks. We reveal fundamental commonalities between these objectives: preserving accurate semantic information is paramount, as it directly dictates the integrity of critical information for intelligent tasks and aids human understanding. Concurrently, enhanced perceptual quality not only improves visual appeal but also, by ensuring realistic image distributions, benefits semantic feature extraction for machine tasks. Based on this insight, we propose Diff-ICMH, a generative image compression framework aiming for harmonizing machine and human vision in image compression. It ensures perceptual realism by leveraging generative priors and simultaneously guarantees semantic fidelity through the incorporation of Semantic Consistency loss (SC loss) during training. Additionally, we introduce the Tag Guidance Module (TGM) that leverages highly semantic image-level tags to stimulate the pre-trained diffusion model's generative capabilities, requiring minimal additional bit rates. Consequently, Diff-ICMH supports multiple intelligent tasks through a single codec and bitstream without any task-specific adaptation, while preserving high-quality visual experience for human perception. Extensive experimental results demonstrate Diff-ICMH's superiority and generalizability across diverse tasks, while maintaining visual appeal for human perception.

A primary challenge in robotic tool use is achieving precise manipulation with dexterous robotic hands to mimic human actions. It requires understanding human tool use and allocating specific functions to each robotic finger for fine control. Existing work has primarily focused on the overall grasping capabilities of robotic hands, often neglecting the functional allocation among individual fingers during object interaction. In response to this, we introduce a semantic knowledge-driven approach to distribute functions among fingers for tool manipulation. Central to this approach is the finger-to-function (F2F) knowledge graph, which captures human expertise in tool use and establishes relationships between tool attributes, tasks, and manipulation elements, including functional fingers, components, required force, and gestures. We also develop a manipulation element-oriented prediction algorithm using knowledge graph semantic embedding, enhancing the prediction of manipulation elements' speed and accuracy. Additionally, we propose the functionality-integrated adaptive force feedback manipulation (FAFM) module, which integrates manipulation elements with adaptive force feedback to achieve precise finger-level control. Our framework does not rely on extensive annotated data for supervision but utilizes semantic constraints from F2F to guide tool manipulation. The proposed method demonstrates superior performance and generalizability in real-world scenarios, achieving an 8% higher success rate in grasping and manipulation of representative tool instances compared to the existing state-of-the-art methods. The dataset and code are available at https://github.com/yangfan293/F2F.

Prompt learning has been recently introduced into the adaption of pre-trained vision-language models (VLMs) by tuning a set of trainable tokens to replace hand-crafted text templates. Despite the encouraging results achieved, existing methods largely rely on extra annotated data for training. In this paper, we investigate a more realistic scenario, where only the unlabeled test data is available. Existing test-time prompt learning methods often separately learn a prompt for each test sample. However, relying solely on a single sample heavily limits the performance of the learned prompts, as it neglects the task-level knowledge that can be gained from multiple samples. To that end, we propose a novel test-time prompt learning method of VLMs, called Task-to-Instance PromPt LEarning (TIPPLE), which adopts a two-stage training strategy to leverage both task- and instance-level knowledge. Specifically, we reformulate the effective online pseudo-labeling paradigm along with two tailored components: an auxiliary text classification task and a diversity regularization term, to serve the task-oriented prompt learning. After that, the learned task-level prompt is further combined with a tunable residual for each test sample to integrate with instance-level knowledge. We demonstrate the superior performance of TIPPLE on 15 downstream datasets, e.g., the average improvement of 1.87% over the state-of-the-art method, using ViT-B/16 visual backbone. Our code is open-sourced at https://github.com/zhiheLu/TIPPLE.

Deep neural networks (DNNs) have shown great potential in no-reference image quality assessment (NR-IQA). However, the annotation of NR-IQA is labor-intensive and time-consuming, which severely limits its application, especially for authentic images. To relieve the dependence on quality annotation, some works have applied unsupervised domain adaptation (UDA) to NR-IQA. However, the above methods ignore the fact that the alignment space used in classification is sub-optimal, since the space is not elaborately designed for perception. To solve this challenge, we propose an effective perception-oriented unsupervised domain adaptation methodStyleAM(StyleAlignment andMixup) for NR-IQA, which transfers sufficient knowledge from label-rich source domain data to label-free target domain images. Specifically, we find a more compact and reliable space i.e., feature style space for perception-oriented UDA based on an interesting observation, that the feature style (i.e., the mean and variance) of the deep layer in DNNs is exactly associated with the quality score in NR-IQA. Therefore, we propose to align the source and target domains in a more perceptual-oriented space i.e., the feature style space, to reduce the intervention from other quality-irrelevant feature factors. Furthermore, to increase the consistency (i.e., ordinal/continuous characteristics) between quality score and its feature style, we also propose a novel feature augmentation strategy Style Mixup, which mixes the feature styles (i.e., the mean and variance) before the last layer of DNNs together with mixing their labels. Extensive experimental results on many cross-domain settings (e.g., synthetic to authentic, and multiple distortions to one distortion) have demonstrated the effectiveness of our proposed StyleAM on NR-IQA.

Generative Adversarial Networks (GANs) have been widely used to recover vivid textures in image super-resolution (SR) tasks. In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world high-quality images in an adversarial training manner. However, the distribution learning is overly coarse-grained, which is susceptible to virtual textures and causes counter-intuitive generation results. To mitigate this, we propose the simple and effective Semantic-aware Discriminator (denoted as SeD), which encourages the SR network to learn the fine-grained distributions by introducing the semantics of images as a condition. Concretely, we aim to excavate the semantics of images from a well-trained semantic extractor. Under different semantics, the discriminator is able to distinguish the real-fake images individually and adaptively, which guides the SR network to learn the more fine-grained semantic-aware textures. To obtain accurate and abundant semantics, we take full advantage of recently popular pretrained vision models (PVMs) with extensive datasets, and then incorporate its semantic features into the discriminator through a well-designed spatial cross-attention module. In this way, our proposed semantic-aware discriminator empowered the SR network to produce more photo-realistic and pleasing images. Extensive experiments on two typical tasks, i.e., SR and Real SR have demonstrated the effectiveness of our proposed methods. The code will be available at https://github.com/1bc12345/SeD.

Short-form UGC video platforms, like Kwai and TikTok, have been an emerging and irreplaceable mainstream media form, thriving on user-friendly engagement, and kaleidoscope creation, etc. However, the advancing content-generation modes, e.g., special effects, and sophisticated processing workflows, e.g., de-artifacts, have introduced significant challenges to recent UGC video quality assessment: (i) the ambiguous contents hinder the identification of quality-determined regions. (ii) the diverse and complicated hybrid distortions are hard to distinguish. To tackle the above challenges and assist in the development of short-form videos, we establish the first large-scale Kwai short Video database for Quality assessment, termed KVQ, which comprises 600 user-uploaded short videos and 3600 processed videos through the diverse practical processing workflows, including preprocessing, transcoding, and enhancement. Among them, the absolute quality score of each video and partial ranking score among indistinguish samples are provided by a team of professional researchers specializing in image processing. Based on this database, we propose the first short-form video quality evaluator, i.e., KSVQE, which enables the quality evaluator to identify the quality-determined semantics with the content understanding of large vision language models (i.e., CLIP) and distinguish the distortions with the distortion understanding module. Experimental results have shown the effectiveness of KSVQE on our KVQ database and popular VQA databases. The project can be found at https://lixinustc.github.io/projects/KVQ/.

Neural Radiance Field (NeRF) has achieved superior performance for novel view synthesis by modeling the scene with a Multi-Layer Perception (MLP) and a volume rendering procedure, however, when fewer known views are given (i.e., few-shot view synthesis), the model is prone to overfit the given views. To handle this issue, previous efforts have been made towards leveraging learned priors or introducing additional regularizations. In contrast, in this paper, we for the first time provide an orthogonal method from the perspective of network structure. Given the observation that trivially reducing the number of model parameters alleviates the overfitting issue, but at the cost of missing details, we propose the multi-input MLP (mi-MLP) that incorpo-rates the inputs (i.e., location and viewing direction) of the vanilla MLP into each layer to prevent the overfitting issue without harming detailed synthesis. To further reduce the artifacts, we propose to model colors and volume density separately and present two regularization terms. Ex-tensive experiments on multiple datasets demonstrate that: 1) although the proposed mi-MLP is easy to implement, it is surprisingly effective as it boosts the PSNR of the base-line from 14.73 to 24.23. 2) the overall framework achieves state-of-the-art results on a wide range of benchmarks.

We introduce an enhanced spatial perception module, as shown in Fig. 1 , pre-trained on multiple image quality assessment datasets, and a lightweight temporal fusion module to address the no-reference visual quality assessment (NR-VQA) task. This model implements Swin Transformer V2 [1] as a local-level spatial feature extractor and fuses these multi-scale features to enhance the quality-aware information. Furthermore, a temporal transformer is utilized for spatiotemporal feature fusion. To accommodate compressed videos of varying bitrates, we incorporate a coarse-to-fine contrastive strategy, that is, the group contrast loss is used for coarse discrimination of different bitrates, and the rank loss is used at a fine-grained level to enrich the model’s capability to discriminate different quality level.

User Generated Content (UGC) videos are susceptible to complicated and variant degradations and contents, which prevents the existing blind video quality assessment (BVQA) models from good performance since the lack of the adaptability of distortions and contents. To mitigate this, we propose a novel prior-augmented perceptual vision transformer (PriorFormer) for the BVQA of UGC, which boots its adaptability and representation capability for divergent contents and distortions. Concretely, we introduce two powerful priors, i.e., the content and distortion priors, by extracting the content and distortion embeddings from two pre-trained feature extractors. Then we adopt these two powerful embeddings as the adaptive prior tokens, which are transferred to the vision transformer backbone jointly with implicit quality features. Based on the above strategy, the proposed PriorFormer achieves state-of-the-art performance on three public UGC VQA datasets including KoNViD-1K, LIVE-VQC and YouTube-UGC.

Fine-tuning pre-trained vision-language models (VLMs), e.g., CLIP, for the open-world generalization has gained increasing popularity due to its practical value. However, performance advancements are limited when relying solely on intricate algorithmic designs for a single model, even one exhibiting strong performance, e.g., CLIP-ViT-B/16. This paper, for the first time, explores the collaborative potential of leveraging much weaker VLMs to enhance the generalization of a robust single model. The affirmative findings motivate us to address the generalization problem from a novel perspective, i.e., ensemble of pre-trained VLMs. We introduce three customized ensemble strategies, each tailored to one specific scenario. Firstly, we introduce the zero-shot ensemble, automatically adjusting the logits of different models based on their confidence when only pre-trained VLMs are available. Furthermore, for scenarios with extra few-shot samples, we propose the training-free and tuning ensemble, offering flexibility based on the availability of computing resources. The code is available at https://github.com/zhiheLu/Ensemble_VLM.git.

Vision transformer has demonstrated great potential in abundant vision tasks. However, it also inevitably suffers from poor generalization capability when the distribution shift occurs in testing (i.e., out-of-distribution data). To mitigate this issue, we propose a novel method, Semantic-aware Message Broadcasting (SAMB), which enables more informative and flexible feature alignment for unsupervised domain adaptation (UDA). Particularly, we study the attention module in the vision transformer and notice that the alignment space using one global class token lacks enough flexibility, where it interacts information with all image tokens in the same manner but ignores the rich semantics of different regions. In this paper, we aim to improve the richness of the alignment features by enabling semantic-aware adaptive message broadcasting. Particularly, we introduce a group of learned group tokens as nodes to aggregate the global information from all image tokens, but encourage different group tokens to adaptively focus on the message broadcasting to different semantic regions. In this way, our message broadcasting encourages the group tokens to learn more informative and diverse information for effective domain alignment. Moreover, we systematically study the effects of adversarial-based feature alignment (ADA) and pseudo-label based self-training (PST) on UDA. We find that one simple two-stage training strategy with the cooperation of ADA and PST can further improve the adaptation capability of the vision transformer. Extensive experiments on DomainNet, OfficeHome, and VisDA-2017 demonstrate the effectiveness of our methods for UDA.

Blind Image Quality Assessment (BIQA) is susceptible to poor transferability when the distribution shift occurs, e.g., from synthesis degradation to authentic degradation. To mitigate this, some studies have attempted to design unsupervised domain adaptation (UDA) based schemes for BIQA, which intends to eliminate the domain shift through adversarial-based feature alignment. However, the feature alignment is usually taken at the low-frequency space of features since the global average pooling operation. This ignores the transferable perception knowledge in other frequency components and causes the sub-optimal solution for the UDA of BIQA. To overcome this, from a novel frequency perspective, we propose an effective alignment strategy, i.e., Frequency Alignment (dubbed FreqAlign), to excavate the perception-oriented transferability of BIQA in the frequency space. Concretely, we study what frequency components of features are more proper for perception-oriented alignment. Based on this, we propose to improve the perception-oriented transferability of BIQA by performing feature frequency decomposition and selecting the frequency components that contained the most transferable perception knowledge for alignment. To achieve a stable and effective frequency selection, we further propose the frequency movement with a sliding window to find the optimal frequencies for alignment, which is composed of three strategies, i.e., warm up with pre-training, frequency movement-based selection, and perturbation-based finetuning. Extensive experiments under different domain adaptation settings of BIQA have validated the effectiveness of our proposed method.

Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieved great success. However, existing automated DA methods generally perform the search at the image level, which limits the exploration of diversity in local regions. In this paper, we propose a more fine-grained automated DA approach, dubbed Patch AutoAugment, to divide an image into a grid of patches and search for the joint optimal augmentation policies for the patches. We formulate it as a multi-agent reinforcement learning (MARL) problem, where each agent learns an augmentation policy for each patch based on its content together with the semantics of the whole image. The agents cooperate with each other to achieve the optimal augmentation effect of the entire image by sharing a team reward. We show the effectiveness of our method on multiple benchmark datasets of image classification, fine-grained image recognition and object detection (e.g., CIFAR-10, CIFAR-100, ImageNet, CUB-200-2011, Stanford Cars, FGVC-Aircraft and Pascal VOC 2007). Extensive experiments demonstrate that our method outperforms the state-of-the-art DA methods while requiring fewer computational resources.

Data augmentation (DA) has been extensively studied to facilitate model optimization in many tasks. Prior DA works focus on designing augmentation operations themselves, while leaving selecting suitable samples for augmentation out of consideration. This might incur visual ambiguities and further induce training biases. In this paper, we propose an effective approach, dubbed SelectAugment, to select samples for augmentation in a deterministic and online manner based on the sample contents and the network training status. To facilitate the policy learning, in each batch, we exploit the hierarchy of this task by first determining the augmentation ratio and then deciding whether to augment each training sample under this ratio. We model this process as two-step decision-making and adopt Hierarchical Reinforcement Learning (HRL) to learn the selection policy. In this way, the negative effects of the randomness in selecting samples to augment can be effectively alleviated and the effectiveness of DA is improved. Extensive experiments demonstrate that our proposed SelectAugment significantly improves various off-the-shelf DA methods on image classification and fine-grained image recognition.

Recent advances in machine learning have leveraged dramatic increases in computational power, a trend expected to continue in the future. This paper introduces the first Hyperscale Hardware Optimized Neural Architecture Search (H2O-NAS) to automatically design accurate and performant machine learning models tailored to the underlying hardware architecture. H2O-NAS consists of three key components: a new massively parallel “one-shot” search algorithm with intelligent weight sharing, which can scale to search spaces of O(10280) and handle large volumes of production traffic; hardware-optimized search spaces for diverse ML models on heterogeneous hardware; and a novel two-phase hybrid performance model and a multi-objective reward function optimized for large scale deployments.

In recent years, we have witnessed the great advancement of Deep neural networks (DNNs) in image restoration. However, a critical limitation is that they cannot generalize well to real-world degradations with different degrees or types. In this paper, we are the first to propose a novel training strategy for image restoration from the causality perspective, to improve the generalization ability of DNNs for unknown degradations. Our method, termed Distortion Invariant representation Learning (DIL), treats each distortion type and degree as one specific confounder, and learns the distortion-invariant representation by eliminating the harmful confounding effect of each degradation. We derive our DIL with the back-door criterion in causality by modeling the interventions of different distortions from the optimization perspective. Particularly, we introduce counterfactual distortion augmentation to simulate the virtual distortion types and degrees as the confounders. Then, we instantiate the intervention of each distortion with a virtual model updating based on corresponding distorted images, and eliminate them from the meta-learning perspective. Extensive experiments demonstrate the generalization capability of our DIL on unseen distortion types and degrees. Our code will be available at https://github.com/lixinustc/Causal-IR-DIL.

Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) under the low-data regime, where only a few additional parameters are introduced to excavate the task-specific knowledge based on the general and powerful representation of VLMs. However, most adapter-style works face two limitations: (i) modeling task-specific knowledge with a single modality only; and (ii) overlooking the exploitation of the inter-class relationships in downstream tasks, thereby leading to sub-optimal solutions. To mitigate that, we propose an effective adapter-style tuning strategy, dubbed GraphAdapter, which performs the textual adapter by explicitly modeling the dual-modality structure knowledge (i.e., the correlation of different semantics/classes in textual and visual modalities) with a dual knowledge graph. In particular, the dual knowledge graph is established with two sub-graphs, i.e., a textual knowledge sub-graph, and a visual knowledge sub-graph, where the nodes and edges represent the semantics/classes and their correlations in two modalities, respectively. This enables the textual feature of each prompt to leverage the task-specific structure knowledge from both textual and visual modalities, yielding a more effective classifier for downstream tasks. Extensive experimental results on 11 benchmark datasets reveal that our GraphAdapter significantly outperforms the previous adapter-based methods.

Remote medical diagnosis has emerged as a critical and indispensable technique in practical medical systems, where medical data are required to be efficiently compressed and transmitted for diagnosis by either professional doctors or intelligent diagnosis devices. In this process, a large amount of redundant content irrelevant to the diagnosis is subjected to high-fidelity coding, leading to unnecessary transmission costs. To mitigate this, we propose diagnosis-oriented medical image compression, a special semantic compression task designed for medical scenarios, targeting to reduce the compression cost without compromising the diagnosis accuracy. However, collecting sufficient medical data to optimize such a compression system is significantly expensive and challenging due to privacy issues and the lack of professional annotation. In this study, we propose DMIC, the first efficient transfer learning-based codec, for diagnosis-oriented medical image compression, which can be effectively optimized with only few-shot annotated medical examples, by reusing the knowledge in the existing reinforcement learning-based task-driven semantic coding framework, i.e., HRLVSC [1]. Concretely, we focus on tuning only the partial parameters of the policy network for bit allocation within HRLVSC, which enables it to adapt to the medical images. In this work, we validate our DMIC with the typical medical task, Coronary Artery Segmentation. Extensive experiments have demonstrated that our DMIC can achieve 47.594%BD-Rate savings compared to the HEVC anchor, by tuning only the A2C module (2.7% parameters) of the policy network with only 1 medical sample.

Geometry-based point cloud compression (G-PCC), as a prevalent compression technique, has achieved remarkable compression efficiency, thereby significantly reducing the cost of transmission and storage. However, the compressed point clouds inevitably suffer from severe compression artifacts, i.e., geometry distortion, when the compression ratio increases. To address this, we propose the DensityFormer, the first transformer-based network to restore the geometry distortion in the compressed point cloud. Particularly, our approach focuses on two prominent challenges for this: i) the discrete points demand more stringent requirements for long-range contextual information modeling and ii) the point cloud exhibits a non-uniformed point distribution. For the first challenge, our DensityFormer introduce the Swin Transformer-based hierarchical encoder-decoder architecture, intending to model the multi-grained global contextual information for geometric restoration, based on the superior long-range dependency modeling capability of 3D Swin Transformer block. To solve the second challenge, we propose the density-aware Swin Transformer block on the basis of the intuition that the local density of the point cloud can identify the distribution of points, thereby enabling the adaptive non-uniformed restoration for compressed point clouds. By incorporating the above two advanced techniques, our DensityFormer has shown superior restoration capability on multiple typical benchmark datasets, which outperforms existing state-of-the-art (SOTA) methods by an average of 0.55 dB.

The image distortions are complex and dynamically changing in the real-world scenario, due to the fast development of the image processing system. The blind image quality assessment (BIQA) models may encounter the challenge of processing images with distortion types never seen before deployment. However, existing BIQA models generally cannot evolve with unseen distortion types adaptively, which greatly limits the deployment and application of BIQA models in real-world scenarios. To address this problem, we propose a novel Lifelong blind Image Quality Assessment (LIQA) approach, targeting to achieve the lifelong learning of BIQA. Without accessing to previous training data, our proposed LIQA can not only learn new knowledge, but also mitigate the catastrophic forgetting of learned knowledge. Specifically, we adopt the Split-and-Merge distillation strategy to train a single-head network that makes task-agnostic predictions. In the split stage, we first employ a distortion-specific generator to generate pseudo features of each previously seen distortion. Then, we utilize an auxiliary multi-head regression network to keep the response of each distortion. In the merge stage, we replay the pseudo features and use the pseudo labels generated by the auxiliary multi-head network to distill the knowledge of the multiple heads, which can build the final regression single head. Extensive experiments demonstrate that LIQA can perform well in handling both inner-dataset distortion shift and cross-dataset distortion shift. More importantly, our model can achieve stable performance even if the task sequences are long.

As a commonly-used image compression format, JPEG has been broadly applied in the transmission and storage of images. To further reduce the compression cost while maintaining the quality of JPEG images, lossless transcoding technology has been proposed to recompress the compressed JPEG image in the DCT domain. Previous works, on the other hand, typically reduce the redundancy of DCT coefficients and optimize the probability prediction of entropy coding in a hand-crafted manner that lacks generalization ability and flexibility. To tackle the above challenge, we propose the learned lossless JPEG transcoding framework via Joint Lossy and Residual Compression. Instead of directly optimizing the entropy estimation, we focus on the redundancy that exists in the DCT coefficients. To the best of our knowledge, we are the first to utilize the learned end-to-end lossy transform coding to reduce the redundancy of DCT coefficients in a compact representational domain. We also introduce residual compression for lossless transcoding, which adaptively learns the distribution of residual DCT coefficients before compressing them using context-based entropy coding. Our proposed transcoding architecture shows significant superiority in the compression of JPEG images thanks to the collaboration of learned lossy transform coding and residual entropy coding. Extensive experi-ments on multiple datasets have demonstrated that our proposed framework can achieve about 21.49% bits saving in average based on JPEG compression, which outperforms the typical lossless transcoding framework JPEG-XL by 3.51%.

The rapid development of intelligent tasks, e.g., segmentation, detection, and classification, etc, has brought an urgent need for semantic compression, which aims to reduce the compression cost while maintaining the original semantic information. However, it is impractical to directly integrate the semantic metric into the traditional codecs since they cannot be optimized in an end-to-end manner. To solve this problem, some pioneering works have applied reinforcement learning to implement image-wise semantic compression. Nevertheless, the video semantic compression has not been explored since its complex reference architectures and compression modes. In this paper, we take a step forward to video semantic compression and propose the Hierarchical Reinforcement Learning based task-driven Video Semantic Coding, named as HRLVSC. Specifically, to simplify the complex mode decision of video semantic coding, we divided the action space into frame-level and CTU-level spaces in a hierarchical manner, and then explore the best mode selection for them progressively with the cooperation of frame-level and CTU-level agents. Moreover, since the modes of video semantic coding will exponentially increase with the number of frames in a Group of Pictures (GOP), we carefully investigate the effects of different mode selections for video semantic coding, and design a simple but effective mode simplification strategy for it. We have validated our HRLVSC on video segmentation task with HEVC reference software HM16.19. Extensive experimental results demonstrated that our HRLVSC can achieve over 39% BD-rate saving for video semantic coding under the Low Delay P configuration.

Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications. First, parallel acceleration of the autoregressive entropy model cannot be achieved due to serial decoding. Second, full-resolution inference often causes the out-of-memory (OOM) problem with limited GPU resources, especially for high-resolution images. Block partition is a good choice to handle the above issues, but it brings about new challenges in reducing the redundancy between blocks and eliminating block effects. To tackle the above challenges, this paper provides a learned block-based hybrid image compression (LBHIC) framework. Specifically, we introduce explicit intra prediction into a learned image compression framework to utilize the relation among adjacent blocks. Superior to context modeling by linear weighting of neighbor pixels in traditional codecs, we propose a contextual prediction module (CPM) to better capture long-range correlations by utilizing the strip pooling to extract the most relevant information in neighboring latent space, thus achieving effective information prediction. Moreover, to alleviate blocking artifacts, we further propose a boundary-aware postprocessing module (BPM) with the edge importance taken into account. Extensive experiments demonstrate that the proposed LBHIC codec outperforms the VVC, with a bit-rate conservation of 4.1%, and reduces the decoding time by approximately 86.7% compared with that of state-of-the-art learned image compression methods.

Unsupervised single image restoration approach, Deep Image Prior (DIP), aims to restore images by learning enough raw image statistic priors from the corrupted observation. However, it is not uncommon that an image is contaminated by the multiple unknown distortions. Thus it is hard to disentangle the clean and the hybrid distortion signals by solely relying on image prior learning to restore the images. To overcome this problem, we propose the Dual Prior Learning (DPL) method by taking both image and distortion priors into account. DPL goes beyond DIP by considering an additional step to explicitly learn the blended distortion prior. Furthermore, to coordinate the learning of two priors and avoid them learning the same knowledge, we exploit unpaired training data to enforce a weakly supervision in an adversarial manner to encourage disentangling two priors. Extensive experiments show the effectiveness and appealing performance of the proposed DPL on restoring images with challenging unknown blended distortions.

Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolution (RealSR) problem lies in learning feature representations that are both informative and content-aware. In this paper, we propose a Omni-frequency Region-adaptive Network (OR-Net) to address both challenges, here we call features of all low, middle and high frequencies omni-frequency features. Specifically, we start from the frequency perspective and design a Frequency Decomposition (FD) module to separate different frequency components to comprehensively compensate the information lost for real LR image. Then, considering the different regions of real LR image have different frequency information lost, we further design a Region-adaptive Frequency Aggregation (RFA) module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions. The extensive experiments endorse the high-efficient, effective, and scenario-agnostic nature of our OR-Net for RealSR.

Task-driven semantic video/image coding has drawn considerable attention with the development of intelligent media applications, such as license plate detection, face detection, and medical diagnosis, which focuses on maintaining the semantic information of videos/images. Deep neural network (DNN)-based codecs have been studied for this purpose due to their inherent end-to-end optimization mechanism. However, the traditional hybrid coding framework cannot be optimized in an end-to-end manner, which makes task-driven semantic fidelity metric unable to be automatically integrated into the rate-distortion optimization process. Therefore, it is still attractive and challenging to implement task-driven semantic coding with the traditional hybrid coding framework, which should still be widely used in practical industry for a long time. To solve this challenge, we design semantic maps for different tasks to extract the pixelwise semantic fidelity for videos/images. Instead of directly integrating the semantic fidelity metric into traditional hybrid coding framework, we implement task-driven semantic coding by implementing semantic bit allocation based on reinforcement learning (RL). We formulate the semantic bit allocation problem as a Markov decision process (MDP) and utilize one RL agent to automatically determine the quantization parameters (QPs) for different coding units (CUs) according to the task-driven semantic fidelity metric. Extensive experiments on different tasks, such as classification, detection and segmentation, have demonstrated the superior performance of our approach by achieving an average bitrate saving of 34.39% to 52.62% over the High Efficiency Video Coding (H.265/HEVC) anchor under equivalent task-related semantic fidelity.