Siwei Ma

Wenkang Shan, Zhenhua Liu, Xinfeng Zhang et al.

This paper introduces a novel Pre-trained Spatial Temporal Many-to-One (P-STMO) model for 2D-to-3D human pose estimation task. To reduce the difficulty of capturing spatial and temporal information, we divide this task into two stages: pre-training (Stage I) and fine-tuning (Stage II). In Stage I, a self-supervised pre-training sub-task, termed masked pose modeling, is proposed. The human joints in the input sequence are randomly masked in both spatial and temporal domains. A general form of denoising auto-encoder is exploited to recover the original 2D poses and the encoder is capable of capturing spatial and temporal dependencies in this way. In Stage II, the pre-trained encoder is loaded to STMO model and fine-tuned. The encoder is followed by a many-to-one frame aggregator to predict the 3D pose in the current frame. Especially, an MLP block is utilized as the spatial feature extractor in STMO, which yields better performance than other methods. In addition, a temporal downsampling strategy is proposed to diminish data redundancy. Extensive experiments on two benchmarks show that our method outperforms state-of-the-art methods with fewer parameters and less computational overhead. For example, our P-STMO model achieves 42.1mm MPJPE on Human3.6M dataset when using 2D poses from CPN as inputs. Meanwhile, it brings a 1.5-7.1 times speedup to state-of-the-art methods. Code is available at https://github.com/paTRICK-swk/P-STMO.

Wenkang Shan, Zhenhua Liu, Xinfeng Zhang et al.

In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) is proposed for probabilistic 3D human pose estimation. On the one hand, D3DP generates multiple possible 3D pose hypotheses for a single 2D observation. It gradually diffuses the ground truth 3D poses to a random distribution, and learns a denoiser conditioned on 2D keypoints to recover the uncontaminated 3D poses. The proposed D3DP is compatible with existing 3D pose estimators and supports users to balance efficiency and accuracy during inference through two customizable parameters. On the other hand, JPMA is proposed to assemble multiple hypotheses generated by D3DP into a single 3D pose for practical use. It reprojects 3D pose hypotheses to the 2D camera plane, selects the best hypothesis joint-by-joint based on the reprojection errors, and combines the selected joints into the final pose. The proposed JPMA conducts aggregation at the joint level and makes use of the 2D prior information, both of which have been overlooked by previous approaches. Extensive experiments on Human3.6M and MPI-INF-3DHP datasets show that our method outperforms the state-of-the-art deterministic and probabilistic approaches by 1.5% and 8.9%, respectively. Code is available at https://github.com/paTRICK-swk/D3DP.

Jiechong Song, Chong Mou, Shiqi Wang et al.

By integrating certain optimization solvers with deep neural networks, deep unfolding network (DUN) with good interpretability and high performance has attracted growing attention in compressive sensing (CS). However, existing DUNs often improve the visual quality at the price of a large number of parameters and have the problem of feature information loss during iteration. In this paper, we propose an Optimization-inspired Cross-attention Transformer (OCT) module as an iterative process, leading to a lightweight OCT-based Unfolding Framework (OCTUF) for image CS. Specifically, we design a novel Dual Cross Attention (Dual-CA) sub-module, which consists of an Inertia-Supplied Cross Attention (ISCA) block and a Projection-Guided Cross Attention (PGCA) block. ISCA block introduces multi-channel inertia forces and increases the memory effect by a cross attention mechanism between adjacent iterations. And, PGCA block achieves an enhanced information interaction, which introduces the inertia force into the gradient descent step through a cross attention block. Extensive CS experiments manifest that our OCTUF achieves superior performance compared to state-of-the-art methods while training lower complexity. Codes are available at https://github.com/songjiechong/OCTUF.

Qi Zhang, Shanshe Wang, Xinfeng Zhang et al.

Video Coding for Machines (VCM) aims to compress visual signals for machine analysis. However, existing methods only consider a few machines, neglecting the majority. Moreover, the machine's perceptual characteristics are not leveraged effectively, resulting in suboptimal compression efficiency. To overcome these limitations, this paper introduces Satisfied Machine Ratio (SMR), a metric that statistically evaluates the perceptual quality of compressed images and videos for machines by aggregating satisfaction scores from them. Each score is derived from machine perceptual differences between original and compressed images. Targeting image classification and object detection tasks, we build two representative machine libraries for SMR annotation and create a large-scale SMR dataset to facilitate SMR studies. We then propose an SMR prediction model based on the correlation between deep feature differences and SMR. Furthermore, we introduce an auxiliary task to increase the prediction accuracy by predicting the SMR difference between two images in different quality. Extensive experiments demonstrate that SMR models significantly improve compression performance for machines and exhibit robust generalizability on unseen machines, codecs, datasets, and frame types. SMR enables perceptual coding for machines and propels VCM from specificity to generality. Code is available at https://github.com/ywwynm/SMR.

Zheng Chang, Xinfeng Zhang, Shanshe Wang et al.

Although significant achievements have been achieved by recurrent neural network (RNN) based video prediction methods, their performance in datasets with high resolutions is still far from satisfactory because of the information loss problem and the perception-insensitive mean square error (MSE) based loss functions. In this paper, we propose a Spatiotemporal Information-Preserving and Perception-Augmented Model (STIP) to solve the above two problems. To solve the information loss problem, the proposed model aims to preserve the spatiotemporal information for videos during the feature extraction and the state transitions, respectively. Firstly, a Multi-Grained Spatiotemporal Auto-Encoder (MGST-AE) is designed based on the X-Net structure. The proposed MGST-AE can help the decoders recall multi-grained information from the encoders in both the temporal and spatial domains. In this way, more spatiotemporal information can be preserved during the feature extraction for high-resolution videos. Secondly, a Spatiotemporal Gated Recurrent Unit (STGRU) is designed based on the standard Gated Recurrent Unit (GRU) structure, which can efficiently preserve spatiotemporal information during the state transitions. The proposed STGRU can achieve more satisfactory performance with a much lower computation load compared with the popular Long Short-Term (LSTM) based predictive memories. Furthermore, to improve the traditional MSE loss functions, a Learned Perceptual Loss (LP-loss) is further designed based on the Generative Adversarial Networks (GANs), which can help obtain a satisfactory trade-off between the objective quality and the perceptual quality. Experimental results show that the proposed STIP can predict videos with more satisfactory visual quality compared with a variety of state-of-the-art methods. Source code has been available at \url{https://github.com/ZhengChang467/STIPHR}.

Yuqing Liu, Qi Jia, Jian Zhang et al.

Bit-depth expansion (BDE) is one of the emerging technologies to display high bit-depth (HBD) image from low bit-depth (LBD) source. Existing BDE methods have no unified solution for various BDE situations, and directly learn a mapping for each pixel from LBD image to the desired value in HBD image, which may change the given high-order bits and lead to a huge deviation from the ground truth. In this paper, we design a bit restoration network (BRNet) to learn a weight for each pixel, which indicates the ratio of the replenished value within a rational range, invoking an accurate solution without modifying the given high-order bit information. To make the network adaptive for any bit-depth degradation, we investigate the issue in an optimization perspective and train the network under progressive training strategy for better performance. Moreover, we employ Wasserstein distance as a visual quality indicator to evaluate the difference of color distribution between restored image and the ground truth. Experimental results show our method can restore colorful images with fewer artifacts and false contours, and outperforms state-of-the-art methods with higher PSNR/SSIM results and lower Wasserstein distance. The source code will be made available at https://github.com/yuqing-liu-dut/bit-depth-expansion

Yuqing Liu, Qi Jia, Shanshe Wang et al.

Image super-resolution (SR) has been widely investigated in recent years. However, it is challenging to fairly estimate the performance of various SR methods, as the lack of reliable and accurate criteria for the perceptual quality. Existing metrics concentrate on the specific kind of degradation without distinguishing the visual sensitive areas, which have no ability to describe the diverse SR degeneration situations in both low-level textural and high-level perceptual information. In this paper, we focus on the textural and perceptual degradation of SR images, and design a dual stream network to jointly explore the textural and perceptual information for quality assessment, dubbed TPNet. By mimicking the human vision system (HVS) that pays more attention to the significant image areas, we develop the spatial attention to make the visual sensitive information more distinguishable and utilize feature normalization (F-Norm) to boost the network representation. Experimental results show the TPNet predicts the visual quality score more accurate than other methods and demonstrates better consistency with the human's perspective. The source code will be available at \url{http://github.com/yuqing-liu-dut/NRIQA_SR}

Jiguo Li, Chuanmin Jia, Xinfeng Zhang et al.

Traditional image/video compression aims to reduce the transmission/storage cost with signal fidelity as high as possible. However, with the increasing demand for machine analysis and semantic monitoring in recent years, semantic fidelity rather than signal fidelity is becoming another emerging concern in image/video compression. With the recent advances in cross modal translation and generation, in this paper, we propose the cross modal compression~(CMC), a semantic compression framework for visual data, to transform the high redundant visual data~(such as image, video, etc.) into a compact, human-comprehensible domain~(such as text, sketch, semantic map, attributions, etc.), while preserving the semantic. Specifically, we first formulate the CMC problem as a rate-distortion optimization problem. Secondly, we investigate the relationship with the traditional image/video compression and the recent feature compression frameworks, showing the difference between our CMC and these prior frameworks. Then we propose a novel paradigm for CMC to demonstrate its effectiveness. The qualitative and quantitative results show that our proposed CMC can achieve encouraging reconstructed results with an ultrahigh compression ratio, showing better compression performance than the widely used JPEG baseline.

Yuqing Liu, Qi Jia, Jian Zhang et al.

As a highly ill-posed issue, single image super-resolution (SISR) has been widely investigated in recent years. The main task of SISR is to recover the information loss caused by the degradation procedure. According to the Nyquist sampling theory, the degradation leads to aliasing effect and makes it hard to restore the correct textures from low-resolution (LR) images. In practice, there are correlations and self-similarities among the adjacent patches in the natural images. This paper considers the self-similarity and proposes a hierarchical image super-resolution network (HSRNet) to suppress the influence of aliasing. We consider the SISR issue in the optimization perspective, and propose an iterative solution pattern based on the half-quadratic splitting (HQS) method. To explore the texture with local image prior, we design a hierarchical exploration block (HEB) and progressive increase the receptive field. Furthermore, multi-level spatial attention (MSA) is devised to obtain the relations of adjacent feature and enhance the high-frequency information, which acts as a crucial role for visual experience. Experimental result shows HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.

Zheng Chang, Xinfeng Zhang, Shanshe Wang et al.

Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information and the spatial information for videos in an independent manner but haven't fully explored the correlations between both terms. In this paper, we propose a SpatioTemporal-Aware Unit (STAU) for video prediction and beyond by exploring the significant spatiotemporal correlations in videos. On the one hand, the motion-aware attention weights are learned from the spatial states to help aggregate the temporal states in the temporal domain. On the other hand, the appearance-aware attention weights are learned from the temporal states to help aggregate the spatial states in the spatial domain. In this way, the temporal information and the spatial information can be greatly aware of each other in both domains, during which, the spatiotemporal receptive field can also be greatly broadened for more reliable spatiotemporal modeling. Experiments are not only conducted on traditional video prediction tasks but also other tasks beyond video prediction, including the early action recognition and object detection tasks. Experimental results show that our STAU can outperform other methods on all tasks in terms of performance and computation efficiency.

Kexiang Feng, Chuanmin Jia, Siwei Ma et al.

Recently, the bio-inspired spike camera with continuous motion recording capability has attracted tremendous attention due to its ultra high temporal resolution imaging characteristic. Such imaging feature results in huge data storage and transmission burden compared to that of traditional camera, raising severe challenge and imminent necessity in compression for spike camera captured content. Existing lossy data compression methods could not be applied for compressing spike streams efficiently due to integrate-and-fire characteristic and binarized data structure. Considering the imaging principle and information fidelity of spike cameras, we introduce an effective and robust representation of spike streams. Based on this representation, we propose a novel learned spike compression framework using scene recovery, variational auto-encoder plus spike simulator. To our knowledge, it is the first data-trained model for efficient and robust spike stream compression. Extensive experimental results show that our method outperforms the conventional and learning-based codecs, contributing a strong baseline for learned spike data compression.

Yuefeng Zhang, Chuanmin Jia, Jiannhui Chang et al.

In this age of information, images are a critical medium for storing and transmitting information. With the rapid growth of image data amount, visual compression and visual data perception are two important research topics attracting a lot attention. However, those two topics are rarely discussed together and follow separate research path. Due to the compact compressed domain representation offered by learning-based image compression methods, there exists possibility to have one stream targeting both efficient data storage and compression, and machine perception tasks. In this paper, we propose a layered generative image compression model achieving high human vision-oriented image reconstructed quality, even at extreme compression ratios. To obtain analysis efficiency and flexibility, a task-agnostic learning-based compression model is proposed, which effectively supports various compressed domain-based analytical tasks while reserves outstanding reconstructed perceptual quality, compared with traditional and learning-based codecs. In addition, joint optimization schedule is adopted to acquire best balance point among compression ratio, reconstructed image quality, and downstream perception performance. Experimental results verify that our proposed compressed domain-based multi-task analysis method can achieve comparable analysis results against the RGB image-based methods with up to 99.6% bit rate saving (i.e., compared with taking original RGB image as the analysis model input). The practical ability of our model is further justified from model size and information fidelity aspects.

Linzhi Wu, Pengjun Xie, Jie Zhou et al.

Self-augmentation has received increasing research interest recently to improve named entity recognition (NER) performance in low-resource scenarios. Token substitution and mixup are two feasible heterogeneous self-augmentation techniques for NER that can achieve effective performance with certain specialized efforts. Noticeably, self-augmentation may introduce potentially noisy augmented data. Prior research has mainly resorted to heuristic rule-based constraints to reduce the noise for specific self-augmentation methods individually. In this paper, we revisit these two typical self-augmentation methods for NER, and propose a unified meta-reweighting strategy for them to achieve a natural integration. Our method is easily extensible, imposing little effort on a specific self-augmentation method. Experiments on different Chinese and English NER benchmarks show that our token substitution and mixup method, as well as their integration, can achieve effective performance improvement. Based on the meta-reweighting mechanism, we can enhance the advantages of the self-augmentation techniques without much extra effort.

Jan Henrik Fitschen, Jianwei Ma, Sebastian Schuff

Focused ion beam (FIB) tomography provides high resolution volumetric images on a micro scale. However, due to the physical acquisition process the resulting images are often corrupted by a so-called curtaining or waterfall effect. In this paper, a new convex variational model for removing such effects is proposed. More precisely, an infimal convolution model is applied to split the corrupted 3D image into the clean image and two types of corruptions, namely a striped part and a laminar one. As regularizing terms different direction dependent first and second order differences are used to cope with the specific structure of the corruptions. This generalizes discrete unidirectional total variational (TV) approaches. A minimizer of the model is computed by well-known primal dual techniques. Numerical examples show the very good performance of our new method for artificial and real-world data. Besides FIB tomography, we have also successfully applied our technique for the removal of pure stripes in Moderate Resolution Imaging Spectroradiometer (MODIS) data.

Chuanmin Jia, Feng Ye, Huifang Sun et al.

During the past decade, the Unmanned-Aerial-Vehicles (UAVs) have attracted increasing attention due to their flexible, extensive, and dynamic space-sensing capabilities. The volume of video captured by UAVs is exponentially growing along with the increased bitrate generated by the advancement of the sensors mounted on UAVs, bringing new challenges for on-device UAV storage and air-ground data transmission. Most existing video compression schemes were designed for natural scenes without consideration of specific texture and view characteristics of UAV videos. In this work, we first contribute a detailed analysis of the current state of the field of UAV video coding. Then we propose to establish a novel task for learned UAV video coding and construct a comprehensive and systematic benchmark for such a task, present a thorough review of high quality UAV video datasets and benchmarks, and contribute extensive rate-distortion efficiency comparison of learned and conventional codecs after. Finally, we discuss the challenges of encoding UAV videos. It is expected that the benchmark will accelerate the research and development in video coding on drone platforms.

Yanqi Wu, Hossein S. Aghamiry, Stephane Operto et al.

Frequency-domain simulation of seismic waves plays an important role in seismic inversion, but it remains challenging in large models. The recently proposed physics-informed neural network (PINN), as an effective deep learning method, has achieved successful applications in solving a wide range of partial differential equations (PDEs), and there is still room for improvement on this front. For example, PINN can lead to inaccurate solutions when PDE coefficients are non-smooth and describe structurally-complex media. In this paper, we solve the acoustic and visco-acoustic scattered-field wave equation in the frequency domain with PINN instead of the wave equation to remove source singularity. We first illustrate that non-smooth velocity models lead to inaccurate wavefields when no boundary conditions are implemented in the loss function. Then, we add the perfectly matched layer (PML) conditions in the loss function of PINN and design a quadratic neural network to overcome the detrimental effects of non-smooth models in PINN. We show that PML and quadratic neurons improve the results as well as attenuation and discuss the reason for this improvement. We also illustrate that a network trained during a wavefield simulation can be used to pre-train the neural network of another wavefield simulation after PDE-coefficient alteration and improve the convergence speed accordingly. This pre-training strategy should find application in iterative full waveform inversion (FWI) and time-lag target-oriented imaging when the model perturbation between two consecutive iterations or two consecutive experiments can be small.

Qi Mao, Tinghan Yang, Yinuo Zhang et al.

Recent advances in generative compression methods have demonstrated remarkable progress in enhancing the perceptual quality of compressed data, especially in scenarios with low bitrates. However, their efficacy and applicability to achieve extreme compression ratios ($<0.05$ bpp) remain constrained. In this work, we propose a simple yet effective coding framework by introducing vector quantization (VQ)--based generative models into the image compression domain. The main insight is that the codebook learned by the VQGAN model yields a strong expressive capacity, facilitating efficient compression of continuous information in the latent space while maintaining reconstruction quality. Specifically, an image can be represented as VQ-indices by finding the nearest codeword, which can be encoded using lossless compression methods into bitstreams. We propose clustering a pre-trained large-scale codebook into smaller codebooks through the K-means algorithm, yielding variable bitrates and different levels of reconstruction quality within the coding framework. Furthermore, we introduce a transformer to predict lost indices and restore images in unstable environments. Extensive qualitative and quantitative experiments on various benchmark datasets demonstrate that the proposed framework outperforms state-of-the-art codecs in terms of perceptual quality-oriented metrics and human perception at extremely low bitrates ($\le 0.04$ bpp). Remarkably, even with the loss of up to $20\%$ of indices, the images can be effectively restored with minimal perceptual loss.

Yanbo Gao, Wenjia Huang, Shuai Li et al.

Learned video compression (LVC) has witnessed remarkable advancements in recent years. Similar as the traditional video coding, LVC inherits motion estimation/compensation, residual coding and other modules, all of which are implemented with neural networks (NNs). However, within the framework of NNs and its training mechanism using gradient backpropagation, most existing works often struggle to consistently generate stable motion information, which is in the form of geometric features, from the input color features. Moreover, the modules such as the inter-prediction and residual coding are independent from each other, making it inefficient to fully reduce the spatial-temporal redundancy. To address the above problems, in this paper, we propose a novel Spatial-Temporal Transformer based Video Compression (STT-VC) framework. It contains a Relaxed Deformable Transformer (RDT) with Uformer based offsets estimation for motion estimation and compensation, a Multi-Granularity Prediction (MGP) module based on multi-reference frames for prediction refinement, and a Spatial Feature Distribution prior based Transformer (SFD-T) for efficient temporal-spatial joint residual compression. Specifically, RDT is developed to stably estimate the motion information between frames by thoroughly investigating the relationship between the similarity based geometric motion feature extraction and self-attention. MGP is designed to fuse the multi-reference frame information by effectively exploring the coarse-grained prediction feature generated with the coded motion information. SFD-T is to compress the residual information by jointly exploring the spatial feature distributions in both residual and temporal prediction to further reduce the spatial-temporal redundancy. Experimental results demonstrate that our method achieves the best result with 13.5% BD-Rate saving over VTM.

Kun Qiu, Harry Chang, Ying Wang et al.

Sophisticated traffic analytics, such as the encrypted traffic analytics and unknown malware detection, emphasizes the need for advanced methods to analyze the network traffic. Traditional methods of using fixed patterns, signature matching, and rules to detect known patterns in network traffic are being replaced with AI (Artificial Intelligence) driven algorithms. However, the absence of a high-performance AI networking-specific framework makes deploying real-time AI-based processing within networking workloads impossible. In this paper, we describe the design of Traffic Analytics Development Kits (TADK), an industry-standard framework specific for AI-based networking workloads processing. TADK can provide real-time AI-based networking workload processing in networking equipment from the data center out to the edge without the need for specialized hardware (e.g., GPUs, Neural Processing Unit, and so on). We have deployed TADK in commodity WAF and 5G UPF, and the evaluation result shows that TADK can achieve a throughput up to 35.3Gbps per core on traffic feature extraction, 6.5Gbps per core on traffic classification, and can decrease SQLi/XSS detection down to 4.5us per request with higher accuracy than fixed pattern solution.

Xianping Ma, Xiaokang Zhang, Xingchen Ding et al.

Unsupervised domain adaptation (UDA) techniques are vital for semantic segmentation in geosciences, effectively utilizing remote sensing imagery across diverse domains. However, most existing UDA methods, which focus on domain alignment at the high-level feature space, struggle to simultaneously retain local spatial details and global contextual semantics. To overcome these challenges, a novel decomposition scheme is proposed to guide domain-invariant representation learning. Specifically, multiscale high/low-frequency decomposition (HLFD) modules are proposed to decompose feature maps into high- and low-frequency components across different subspaces. This decomposition is integrated into a fully global-local generative adversarial network (GLGAN) that incorporates global-local transformer blocks (GLTBs) to enhance the alignment of decomposed features. By integrating the HLFD scheme and the GLGAN, a novel decomposition-based UDA framework called De-GLGAN is developed to improve the cross-domain transferability and generalization capability of semantic segmentation models. Extensive experiments on two UDA benchmarks, namely ISPRS Potsdam and Vaihingen, and LoveDA Rural and Urban, demonstrate the effectiveness and superiority of the proposed approach over existing state-of-the-art UDA methods. The source code for this work is accessible at https://github.com/sstary/SSRS.

Zhangpu Li, Changhong Zou, Suxue Ma et al.

The rocketing prosperity of large language models (LLMs) in recent years has boosted the prevalence of vision-language models (VLMs) in the medical sector. In our online medical consultation scenario, a doctor responds to the texts and images provided by a patient in multiple rounds to diagnose her/his health condition, forming a multi-turn multimodal medical dialogue format. Unlike high-quality images captured by professional equipment in traditional medical visual question answering (Med-VQA), the images in our case are taken by patients' mobile phones. These images have poor quality control, with issues such as excessive background elements and the lesion area being significantly off-center, leading to degradation of vision-language alignment in the model training phase. In this paper, we propose ZALM3, a Zero-shot strategy to improve vision-language ALignment in Multi-turn Multimodal Medical dialogue. Since we observe that the preceding text conversations before an image can infer the regions of interest (RoIs) in the image, ZALM3 employs an LLM to summarize the keywords from the preceding context and a visual grounding model to extract the RoIs. The updated images eliminate unnecessary background noise and provide more effective vision-language alignment. To better evaluate our proposed method, we design a new subjective assessment metric for multi-turn unimodal/multimodal medical dialogue to provide a fine-grained performance comparison. Our experiments across three different clinical departments remarkably demonstrate the efficacy of ZALM3 with statistical significance.

Qi Mao, Hao Cheng, Tinghan Yang et al.

We present GNVC-VD, the first DiT-based generative neural video compression framework built upon an advanced video generation foundation model, where spatio-temporal latent compression and sequence-level generative refinement are unified within a single codec. Existing perceptual codecs primarily rely on pre-trained image generative priors to restore high-frequency details, but their frame-wise nature lacks temporal modeling and inevitably leads to perceptual flickering. To address this, GNVC-VD introduces a unified flow-matching latent refinement module that leverages a video diffusion transformer to jointly enhance intra- and inter-frame latents through sequence-level denoising, ensuring consistent spatio-temporal details. Instead of denoising from pure Gaussian noise as in video generation, GNVC-VD initializes refinement from decoded spatio-temporal latents and learns a correction term that adapts the diffusion prior to compression-induced degradation. A conditioning adaptor further injects compression-aware cues into intermediate DiT layers, enabling effective artifact removal while maintaining temporal coherence under extreme bitrate constraints. Extensive experiments show that GNVC-VD surpasses both traditional and learned codecs in perceptual quality and significantly reduces the flickering artifacts that persist in prior generative approaches, even below 0.01 bpp, highlighting the promise of integrating video-native generative priors into neural codecs for next-generation perceptual video compression.

Liying Wang, Xiaoli Zhang, Chuanmin Jia et al.

Infrared-visible image fusion methods aim at generating fused images with good visual quality and also facilitate the performance of high-level tasks. Indeed, existing semantic-driven methods have considered semantic information injection for downstream applications. However, none of them investigates the potential for reciprocal promotion between pixel-wise image fusion and cross-modal feature fusion perception tasks from a macroscopic task-level perspective. To address this limitation, we propose a unified network for image fusion and semantic segmentation. MAFS is a parallel structure, containing a fusion sub-network and a segmentation sub-network. On the one hand, We devise a heterogeneous feature fusion strategy to enhance semantic-aware capabilities for image fusion. On the other hand, by cascading the fusion sub-network and a segmentation backbone, segmentation-related knowledge is transferred to promote feature-level fusion-based segmentation. Within the framework, we design a novel multi-stage Transformer decoder to aggregate fine-grained multi-scale fused features efficiently. Additionally, a dynamic factor based on the max-min fairness allocation principle is introduced to generate adaptive weights of two tasks and guarantee smooth training in a multi-task manner. Extensive experiments demonstrate that our approach achieves competitive results compared with state-of-the-art methods. The code is available at https://github.com/Abraham-Einstein/MAFS/.

Xiaoli Zhang, Liying Wang, Libo Zhao et al.

Multi-modality image fusion aims at fusing modality-specific (complementarity) and modality-shared (correlation) information from multiple source images. To tackle the problem of the neglect of inter-feature relationships, high-frequency information loss, and the limited attention to downstream tasks, this paper focuses on how to model correlation-driven decomposing features and reason high-level graph representation by efficiently extracting complementary information and aggregating multi-guided features. We propose a three-branch encoder-decoder architecture along with corresponding fusion layers as the fusion strategy. Firstly, shallow features from individual modalities are extracted by a depthwise convolution layer combined with the transformer block. In the three parallel branches of the encoder, Cross Attention and Invertible Block (CAI) extracts local features and preserves high-frequency texture details. Base Feature Extraction Module (BFE) captures long-range dependencies and enhances modality-shared information. Graph Reasoning Module (GR) is introduced to reason high-level cross-modality relations and simultaneously extract low-level detail features as CAI's modality-specific complementary information. Experiments demonstrate the competitive results compared with state-of-the-art methods in visible/infrared image fusion and medical image fusion tasks. Moreover, the proposed algorithm surpasses the state-of-the-art methods in terms of subsequent tasks, averagely scoring 8.27% mAP@0.5 higher in object detection and 5.85% mIoU higher in semantic segmentation. The code is avaliable at https://github.com/Abraham-Einstein/SMFNet/.

Wei Sun, Xiongkuo Min, Danyang Tu et al.

Image quality assessment (IQA) is very important for both end-users and service providers since a high-quality image can significantly improve the user's quality of experience (QoE) and also benefit lots of computer vision algorithms. Most existing blind image quality assessment (BIQA) models were developed for synthetically distorted images, however, they perform poorly on in-the-wild images, which are widely existed in various practical applications. In this paper, we propose a novel BIQA model for in-the-wild images by addressing two critical problems in this field: how to learn better quality-aware feature representation, and how to solve the problem of insufficient training samples in terms of their content and distortion diversity. Considering that perceptual visual quality is affected by both low-level visual features (e.g. distortions) and high-level semantic information (e.g. content), we first propose a staircase structure to hierarchically integrate the features from intermediate layers into the final feature representation, which enables the model to make full use of visual information from low-level to high-level. Then an iterative mixed database training (IMDT) strategy is proposed to train the BIQA model on multiple databases simultaneously, so the model can benefit from the increase in both training samples and image content and distortion diversity and can learn a more general feature representation. Experimental results show that the proposed model outperforms other state-of-the-art BIQA models on six in-the-wild IQA databases by a large margin. Moreover, the proposed model shows an excellent performance in the cross-database evaluation experiments, which further demonstrates that the learned feature representation is robust to images with diverse distortions and content. The code is available at https://github.com/sunwei925/StairIQA.

Hanting Chen, Yunhe Wang, Tianyu Guo et al.

As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly contributed to the representation ability of transformer and its variant architectures. In this paper, we study the low-level computer vision task (e.g., denoising, super-resolution and deraining) and develop a new pre-trained model, namely, image processing transformer (IPT). To maximally excavate the capability of transformer, we present to utilize the well-known ImageNet benchmark for generating a large amount of corrupted image pairs. The IPT model is trained on these images with multi-heads and multi-tails. In addition, the contrastive learning is introduced for well adapting to different image processing tasks. The pre-trained model can therefore efficiently employed on desired task after fine-tuning. With only one pre-trained model, IPT outperforms the current state-of-the-art methods on various low-level benchmarks. Code is available at https://github.com/huawei-noah/Pretrained-IPT and https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/IPT

Jiarui Meng, Haijie Li, Yanmin Wu et al. · pku

3D Gaussian Splatting (3DGS) has significantly advanced 3D scene reconstruction and novel view synthesis. However, like Neural Radiance Fields (NeRF), 3DGS struggles with accurately modeling physical reflections, particularly in mirrors, leading to incorrect reconstructions and inconsistent reflective properties. To address this challenge, we introduce Mirror-3DGS, a novel framework designed to accurately handle mirror geometries and reflections, thereby generating realistic mirror reflections. By incorporating mirror attributes into 3DGS and leveraging plane mirror imaging principles, Mirror-3DGS simulates a mirrored viewpoint from behind the mirror, enhancing the realism of scene renderings. Extensive evaluations on both synthetic and real-world scenes demonstrate that our method can render novel views with improved fidelity in real-time, surpassing the state-of-the-art Mirror-NeRF, especially in mirror regions.

Qi Mao, Chongyu Wang, Meng Wang et al.

The accelerated proliferation of visual content and the rapid development of machine vision technologies bring significant challenges in delivering visual data on a gigantic scale, which shall be effectively represented to satisfy both human and machine requirements. In this work, we investigate how hierarchical representations derived from the advanced generative prior facilitate constructing an efficient scalable coding paradigm for human-machine collaborative vision. Our key insight is that by exploiting the StyleGAN prior, we can learn three-layered representations encoding hierarchical semantics, which are elaborately designed into the basic, middle, and enhanced layers, supporting machine intelligence and human visual perception in a progressive fashion. With the aim of achieving efficient compression, we propose the layer-wise scalable entropy transformer to reduce the redundancy between layers. Based on the multi-task scalable rate-distortion objective, the proposed scheme is jointly optimized to achieve optimal machine analysis performance, human perception experience, and compression ratio. We validate the proposed paradigm's feasibility in face image compression. Extensive qualitative and quantitative experimental results demonstrate the superiority of the proposed paradigm over the latest compression standard Versatile Video Coding (VVC) in terms of both machine analysis as well as human perception at extremely low bitrates ($<0.01$ bpp), offering new insights for human-machine collaborative compression.

Naifu Xue, Qi Mao, Zijian Wang et al.

Recent progress in generative compression technology has significantly improved the perceptual quality of compressed data. However, these advancements primarily focus on producing high-frequency details, often overlooking the ability of generative models to capture the prior distribution of image content, thus impeding further bitrate reduction in extreme compression scenarios (<0.05 bpp). Motivated by the capabilities of predictive language models for lossless compression, this paper introduces a novel Unified Image Generation-Compression (UIGC) paradigm, merging the processes of generation and compression. A key feature of the UIGC framework is the adoption of vector-quantized (VQ) image models for tokenization, alongside a multi-stage transformer designed to exploit spatial contextual information for modeling the prior distribution. As such, the dual-purpose framework effectively utilizes the learned prior for entropy estimation and assists in the regeneration of lost tokens. Extensive experiments demonstrate the superiority of the proposed UIGC framework over existing codecs in perceptual quality and human perception, particularly in ultra-low bitrate scenarios (<=0.03 bpp), pioneering a new direction in generative compression.

Tiange Zhang, Xiandong Meng, Siwei Ma

Recent advances in end-to-end video compression have shown promising results owing to their unified end-to-end learning optimization. However, such generalized frameworks often lack content-specific adaptation, leading to suboptimal compression performance. To address this, this paper proposes a content adaptive based motion alignment framework that improves performance by adapting encoding strategies to diverse content characteristics. Specifically, we first introduce a two-stage flow-guided deformable warping mechanism that refines motion compensation with coarse-to-fine offset prediction and mask modulation, enabling precise feature alignment. Second, we propose a multi-reference quality aware strategy that adjusts distortion weights based on reference quality, and applies it to hierarchical training to reduce error propagation. Third, we integrate a training-free module that downsamples frames by motion magnitude and resolution to obtain smooth motion estimation. Experimental results on standard test datasets demonstrate that our framework CAMA achieves significant improvements over state-of-the-art Neural Video Compression models, achieving a 24.95% BD-rate (PSNR) savings over our baseline model DCVC-TCM, while also outperforming reproduced DCVC-DC and traditional codec HM-16.25.

Zetian Song, Wenhong Duan, Yuhuai Zhang et al.

Representing the Neural Radiance Field (NeRF) with the explicit voxel grid (EVG) is a promising direction for improving NeRFs. However, the EVG representation is not efficient for storage and transmission because of the terrific memory cost. Current methods for compressing EVG mainly inherit the methods designed for neural network compression, such as pruning and quantization, which do not take full advantage of the spatial correlation of voxels. Inspired by prosperous digital image compression techniques, this paper proposes SPC-NeRF, a novel framework applying spatial predictive coding in EVG compression. The proposed framework can remove spatial redundancy efficiently for better compression performance.Moreover, we model the bitrate and design a novel form of the loss function, where we can jointly optimize compression ratio and distortion to achieve higher coding efficiency. Extensive experiments demonstrate that our method can achieve 32% bit saving compared to the state-of-the-art method VQRF on multiple representative test datasets, with comparable training time.

Yanchen Zhao, Wenhong Duan, Chuanmin Jia et al.

In the fourth generation Audio Video coding Standard (AVS4), the Inter Prediction Filter (INTERPF) reduces discontinuities between prediction and adjacent reconstructed pixels in inter prediction. The paper proposes a low complexity learning-based inter prediction (LLIP) method to replace the traditional INTERPF. LLIP enhances the filtering process by leveraging a lightweight neural network model, where parameters can be exported for efficient inference. Specifically, we extract pixels and coordinates utilized by the traditional INTERPF to form the training dataset. Subsequently, we export the weights and biases of the trained neural network model and implement the inference process without any third-party dependency, enabling seamless integration into video codec without relying on Libtorch, thus achieving faster inference speed. Ultimately, we replace the traditional handcraft filtering parameters in INTERPF with the learned optimal filtering parameters. This practical solution makes the combination of deep learning encoding tools with traditional video encoding schemes more efficient. Experimental results show that our approach achieves 0.01%, 0.31%, and 0.25% coding gain for the Y, U, and V components under the random access (RA) configuration on average.

Yanchen Zhao, Wenxuan He, Chuanmin Jia et al.

In this paper, a hybrid video compression framework is proposed that serves as a demonstrative showcase of deep learning-based approaches extending beyond the confines of traditional coding methodologies. The proposed hybrid framework is founded upon the Enhanced Compression Model (ECM), which is a further enhancement of the Versatile Video Coding (VVC) standard. We have augmented the latest ECM reference software with well-designed coding techniques, including block partitioning, deep learning-based loop filter, and the activation of block importance mapping (BIM) which was integrated but previously inactive within ECM, further enhancing coding performance. Compared with ECM-10.0, our method achieves 6.26, 13.33, and 12.33 BD-rate savings for the Y, U, and V components under random access (RA) configuration, respectively.

Haofeng Wang, Yilin Guo, Zehao Li et al.

The Yellow River is China's mother river and a cradle of human civilization. The ancient Yellow River culture is, moreover, an indispensable part of human art history. To conserve and inherit the ancient Yellow River culture, we designed RiverEcho, a real-time interactive system that responds to voice queries using a large language model and a cultural knowledge dataset, delivering explanations through a talking-head digital human. Specifically, we built a knowledge database focused on the ancient Yellow River culture, including the collection of historical texts and the processing pipeline. Experimental results demonstrate that leveraging Retrieval-Augmented Generation (RAG) on the proposed dataset enhances the response quality of the Large Language Model(LLM), enabling the system to generate more professional and informative responses. Our work not only diversifies the means of promoting Yellow River culture but also provides users with deeper cultural insights.

Xiaohan Lu, Jiaye Fu, Jiaqi Zhang et al.

Feed-forward 3D Gaussian Splatting (3DGS) has recently demonstrated promising results for novel view synthesis (NVS) from sparse input views, particularly under narrow-baseline conditions. However, its performance significantly degrades in wide-baseline scenarios due to limited texture details and geometric inconsistencies across views. To address these challenges, in this paper, we propose ProSplat, a two-stage feed-forward framework designed for high-fidelity rendering under wide-baseline conditions. The first stage involves generating 3D Gaussian primitives via a 3DGS generator. In the second stage, rendered views from these primitives are enhanced through an improvement model. Specifically, this improvement model is based on a one-step diffusion model, further optimized by our proposed Maximum Overlap Reference view Injection (MORI) and Distance-Weighted Epipolar Attention (DWEA). MORI supplements missing texture and color by strategically selecting a reference view with maximum viewpoint overlap, while DWEA enforces geometric consistency using epipolar constraints. Additionally, we introduce a divide-and-conquer training strategy that aligns data distributions between the two stages through joint optimization. We evaluate ProSplat on the RealEstate10K and DL3DV-10K datasets under wide-baseline settings. Experimental results demonstrate that ProSplat achieves an average improvement of 1 dB in PSNR compared to recent SOTA methods.

Qi Zhang, Shanshe Wang, Xinfeng Zhang et al.

Nowadays, high-quality images are pursued by both humans for better viewing experience and by machines for more accurate visual analysis. However, images are usually compressed before being consumed, decreasing their quality. It is meaningful to predict the perceptual quality of compressed images for both humans and machines, which guides the optimization for compression. In this paper, we propose a unified approach to address this. Specifically, we create a deep learning-based model to predict Satisfied User Ratio (SUR) and Satisfied Machine Ratio (SMR) of compressed images simultaneously. We first pre-train a feature extractor network on a large-scale SMR-annotated dataset with human perception-related quality labels generated by diverse image quality models, which simulates the acquisition of SUR labels. Then, we propose an MLP-Mixer-based network to predict SUR and SMR by leveraging and fusing the extracted multi-layer features. We introduce a Difference Feature Residual Learning (DFRL) module to learn more discriminative difference features. We further use a Multi-Head Attention Aggregation and Pooling (MHAAP) layer to aggregate difference features and reduce their redundancy. Experimental results indicate that the proposed model significantly outperforms state-of-the-art SUR and SMR prediction methods. Moreover, our joint learning scheme of human and machine perceptual quality prediction tasks is effective at improving the performance of both.

Tiange Zhang, Zhimeng Huang, Xiandong Meng et al.

Neural Video Compression has emerged in recent years, with condition-based frameworks outperforming traditional codecs. However, most existing methods rely solely on the previous frame's features to predict temporal context, leading to two critical issues. First, the short reference window misses long-term dependencies and fine texture details. Second, propagating only feature-level information accumulates errors over frames, causing prediction inaccuracies and loss of subtle textures. To address these, we propose the Long-term Spatio-Temporal Enhanced Context (L-STEC) method. We first extend the reference chain with LSTM to capture long-term dependencies. We then incorporate warped spatial context from the pixel domain, fusing spatio-temporal information through a multi-receptive field network to better preserve reference details. Experimental results show that L-STEC significantly improves compression by enriching contextual information, achieving 37.01% bitrate savings in PSNR and 31.65% in MS-SSIM compared to DCVC-TCM, outperforming both VTM-17.0 and DCVC-FM and establishing new state-of-the-art performance.

Haocheng Tang, Ruoke Yan, Xinhui Yin et al.

Recent advances in 3D Gaussian Splatting (3DGS) have enabled fast, photorealistic rendering of dynamic 3D scenes, showing strong potential in immersive communication. However, in digital human encoding and transmission, the compression methods based on general 3DGS representations are limited by the lack of human priors, resulting in suboptimal bitrate efficiency and reconstruction quality at the decoder side, which hinders their application in streamable 3D avatar systems. We propose HGC-Avatar, a novel Hierarchical Gaussian Compression framework designed for efficient transmission and high-quality rendering of dynamic avatars. Our method disentangles the Gaussian representation into a structural layer, which maps poses to Gaussians via a StyleUNet-based generator, and a motion layer, which leverages the SMPL-X model to represent temporal pose variations compactly and semantically. This hierarchical design supports layer-wise compression, progressive decoding, and controllable rendering from diverse pose inputs such as video sequences or text. Since people are most concerned with facial realism, we incorporate a facial attention mechanism during StyleUNet training to preserve identity and expression details under low-bitrate constraints. Experimental results demonstrate that HGC-Avatar provides a streamable solution for rapid 3D avatar rendering, while significantly outperforming prior methods in both visual quality and compression efficiency.

Haoyu Wang, Hao Tang, Donglin Di et al.

Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment interactions. This often leads to unrealistic or physically implausible movements with inadequate structural coherence. To conquer these challenges, we propose MoSA, which decouples the process of human video generation into two components, i.e., structure generation and appearance generation. MoSA first employs a 3D structure transformer to generate a human motion sequence from the text prompt. The remaining video appearance is then synthesized under the guidance of this structural sequence. We achieve fine-grained control over the sparse human structures by introducing Human-Aware Dynamic Control modules with a dense tracking constraint during training. The modeling of human-environment interactions is improved through the proposed contact constraint. Those two components work comprehensively to ensure the structural and appearance fidelity across the generated videos. This paper also contributes a large-scale human video dataset, which features more complex and diverse motions than existing human video datasets. We conduct comprehensive comparisons between MoSA and a variety of approaches, including general video generation models, human video generation models, and human animation models. Experiments demonstrate that MoSA substantially outperforms existing approaches across the majority of evaluation metrics.

Haofeng Wang, Fangtao Zhou, Qi Zhang et al.

RGB-IR(RGB-Infrared) image pairs are frequently applied simultaneously in various applications like intelligent surveillance. However, as the number of modalities increases, the required data storage and transmission costs also double. Therefore, efficient RGB-IR data compression is essential. This work proposes a joint compression framework for RGB-IR image pair. Specifically, to fully utilize cross-modality prior information for accurate context probability modeling within and between modalities, we propose a Channel-wise Cross-modality Entropy Model (CCEM). Among CCEM, a Low-frequency Context Extraction Block (LCEB) and a Low-frequency Context Fusion Block (LCFB) are designed for extracting and aggregating the global low-frequency information from both modalities, which assist the model in predicting entropy parameters more accurately. Experimental results demonstrate that our approach outperforms existing RGB-IR image pair and single-modality compression methods on LLVIP and KAIST datasets. For instance, the proposed framework achieves a 23.1% bit rate saving on LLVIP dataset compared to the state-of-the-art RGB-IR image codec presented at CVPR 2022.

Zetian Song, Jiaye Fu, Jiaqi Zhang et al.

The recent development of feedforward 3D Gaussian Splatting (3DGS) presents a new paradigm to reconstruct 3D scenes. Using neural networks trained on large-scale multi-view datasets, it can directly infer 3DGS representations from sparse input views. Although the feedforward approach achieves high reconstruction speed, it still suffers from the substantial storage cost of 3D Gaussians. Existing 3DGS compression methods relying on scene-wise optimization are not applicable due to architectural incompatibilities. To overcome this limitation, we propose TinySplat, a complete feedforward approach for generating compact 3D scene representations. Built upon standard feedforward 3DGS methods, TinySplat integrates a training-free compression framework that systematically eliminates key sources of redundancy. Specifically, we introduce View-Projection Transformation (VPT) to reduce geometric redundancy by projecting geometric parameters into a more compact space. We further present Visibility-Aware Basis Reduction (VABR), which mitigates perceptual redundancy by aligning feature energy along dominant viewing directions via basis transformation. Lastly, spatial redundancy is addressed through an off-the-shelf video codec. Comprehensive experimental results on multiple benchmark datasets demonstrate that TinySplat achieves over 100x compression for 3D Gaussian data generated by feedforward methods. Compared to the state-of-the-art compression approach, we achieve comparable quality with only 6% of the storage size. Meanwhile, our compression framework requires only 25% of the encoding time and 1% of the decoding time.

Kexiang Feng, Chuanmin Jia, Siwei Ma et al.

The advent of neuralmorphic spike cameras has garnered significant attention for their ability to capture continuous motion with unparalleled temporal resolution.However, this imaging attribute necessitates considerable resources for binary spike data storage and transmission.In light of compression and spike-driven intelligent applications, we present the notion of Spike Coding for Intelligence (SCI), wherein spike sequences are compressed and optimized for both bit-rate and task performance.Drawing inspiration from the mammalian vision system, we propose a dual-pathway architecture for separate processing of spatial semantics and motion information, which is then merged to produce features for compression.A refinement scheme is also introduced to ensure consistency between decoded features and motion vectors.We further propose a temporal regression approach that integrates various motion dynamics, capitalizing on the advancements in warping and deformation simultaneously.Comprehensive experiments demonstrate our scheme achieves state-of-the-art (SOTA) performance for spike compression and analysis.We achieve an average 17.25% BD-rate reduction compared to SOTA codecs and a 4.3% accuracy improvement over SpiReco for spike-based classification, with 88.26% complexity reduction and 42.41% inference time saving on the encoding side.

Qizhe Wang, Qian Yin, Zhimeng Huang et al.

Cloud gaming is an advanced form of Internet service that necessitates local terminals to decode within limited resources and time latency. Super-Resolution (SR) techniques are often employed on these terminals as an efficient way to reduce the required bit-rate bandwidth for cloud gaming. However, insufficient attention has been paid to SR of compressed game video content. Most SR networks amplify block artifacts and ringing effects in decoded frames while ignoring edge details of game content, leading to unsatisfactory reconstruction results. In this paper, we propose a novel lightweight network called Coding Prior-Guided Super-Resolution (CPGSR) to address the SR challenges in compressed game video content. First, we design a Compressed Domain Guided Block (CDGB) to extract features of different depths from coding priors, which are subsequently integrated with features from the U-net backbone. Then, a series of re-parameterization blocks are utilized for reconstruction. Ultimately, inspired by the quantization in video coding, we propose a partitioned focal frequency loss to effectively guide the model's focus on preserving high-frequency information. Extensive experiments demonstrate the advancement of our approach.

Ziqun Li, Qi Zhang, Xiaofeng Huang et al.

High-efficient image compression is a critical requirement. In several scenarios where multiple modalities of data are captured by different sensors, the auxiliary information from other modalities are not fully leveraged by existing image-only codecs, leading to suboptimal compression efficiency. In this paper, we increase image compression performance with the assistance of point cloud, which is widely adopted in the area of autonomous driving. We first unify the data representation for both modalities to facilitate data processing. Then, we propose the point cloud-assisted neural image codec (PCA-NIC) to enhance the preservation of image texture and structure by utilizing the high-dimensional point cloud information. We further introduce a multi-modal feature fusion transform module (MMFFT) to capture more representative image features, remove redundant information between channels and modalities that are not relevant to the image content. Our work is the first to improve image compression performance using point cloud and achieves state-of-the-art performance.

Florian Bossmann, Jianwei Ma, Wenze wu

Identifying objects in given data is a task frequently encountered in many applications. Finding vehicles or persons in video data, tracking seismic waves in geophysical exploration data, or predicting a storm front movement from meteorological measurements are only some of the possible applications. In many cases, the object of interest changes its form or position from one measurement to another. For example, vehicles in a video may change its position or angle to the camera in each frame. Seismic waves can change its arrival time, frequency, or intensity depending on the sensor position. Storm fronts can change its form and position over time. This complicates the identification and tracking as the algorithm needs to deal with the changing object over the given measurements. In a previous work, the authors presented a new algorithm to solve this problem - Object reconstruction using K-approximation (ORKA). The algorithm can solve the problem at hand but suffers from two disadvantages. On the one hand, the reconstructed object movement is bound to a grid that depends on the data resolution. On the other hand, the complexity of the algorithm increases exponentially with the resolution. We overcome both disadvantages by introducing an iterative strategy that uses a resampling method to create multiple resolutions of the data. In each iteration the resolution is increased to reconstruct more details of the object of interest. This way, we can even go beyond the original resolution by artificially upsampling the data. We give error bounds and a complexity analysis of the new method. Furthermore, we analyze its performance in several numerical experiments as well as on real data. We also give a brief introduction on the original ORKA algorithm. Knowledge of the previous work is thus not required.

Zheng Chang, Xinfeng Zhang, Shanshe Wang et al.

Although many video prediction methods have obtained good performance in low-resolution (64$\sim$128) videos, predictive models for high-resolution (512$\sim$4K) videos have not been fully explored yet, which are more meaningful due to the increasing demand for high-quality videos. Compared with low-resolution videos, high-resolution videos contain richer appearance (spatial) information and more complex motion (temporal) information. In this paper, we propose a Spatiotemporal Residual Predictive Model (STRPM) for high-resolution video prediction. On the one hand, we propose a Spatiotemporal Encoding-Decoding Scheme to preserve more spatiotemporal information for high-resolution videos. In this way, the appearance details for each frame can be greatly preserved. On the other hand, we design a Residual Predictive Memory (RPM) which focuses on modeling the spatiotemporal residual features (STRF) between previous and future frames instead of the whole frame, which can greatly help capture the complex motion information in high-resolution videos. In addition, the proposed RPM can supervise the spatial encoder and temporal encoder to extract different features in the spatial domain and the temporal domain, respectively. Moreover, the proposed model is trained using generative adversarial networks (GANs) with a learned perceptual loss (LP-loss) to improve the perceptual quality of the predictions. Experimental results show that STRPM can generate more satisfactory results compared with various existing methods.

Yuqing Liu, Qi Jia, Xin Fan et al.

It is challenging to restore low-resolution (LR) images to super-resolution (SR) images with correct and clear details. Existing deep learning works almost neglect the inherent structural information of images, which acts as an important role for visual perception of SR results. In this paper, we design a hierarchical feature exploitation network to probe and preserve structural information in a multi-scale feature fusion manner. First, we propose a cross convolution upon traditional edge detectors to localize and represent edge features. Then, cross convolution blocks (CCBs) are designed with feature normalization and channel attention to consider the inherent correlations of features. Finally, we leverage multi-scale feature fusion group (MFFG) to embed the cross convolution blocks and develop the relations of structural features in different scales hierarchically, invoking a lightweight structure-preserving network named as Cross-SRN. Experimental results demonstrate the Cross-SRN achieves competitive or superior restoration performances against the state-of-the-art methods with accurate and clear structural details. Moreover, we set a criterion to select images with rich structural textures. The proposed Cross-SRN outperforms the state-of-the-art methods on the selected benchmark, which demonstrates that our network has a significant advantage in preserving edges.

Zhenhua Liu, Yunhe Wang, Kai Han et al.

Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers are often of sophisticated architectures for extracting powerful feature representations, which are more difficult to be developed on mobile devices. In this paper, we present an effective post-training quantization algorithm for reducing the memory storage and computational costs of vision transformers. Basically, the quantization task can be regarded as finding the optimal low-bit quantization intervals for weights and inputs, respectively. To preserve the functionality of the attention mechanism, we introduce a ranking loss into the conventional quantization objective that aims to keep the relative order of the self-attention results after quantization. Moreover, we thoroughly analyze the relationship between quantization loss of different layers and the feature diversity, and explore a mixed-precision quantization scheme by exploiting the nuclear norm of each attention map and output feature. The effectiveness of the proposed method is verified on several benchmark models and datasets, which outperforms the state-of-the-art post-training quantization algorithms. For instance, we can obtain an 81.29\% top-1 accuracy using DeiT-B model on ImageNet dataset with about 8-bit quantization.

Chuanmin Jia, Ziqing Ge, Shanshe Wang et al.

End-to-end optimized neural image compression (NIC) has obtained superior lossy compression performance recently. In this paper, we consider the problem of rate-distortion (R-D) characteristic analysis and modeling for NIC. We make efforts to formulate the essential mathematical functions to describe the R-D behavior of NIC using deep networks. Thus arbitrary bit-rate points could be elegantly realized by leveraging such model via a single trained network. We propose a plugin-in module to learn the relationship between the target bit-rate and the binary representation for the latent variable of auto-encoder. The proposed scheme resolves the problem of training distinct models to reach different points in the R-D space. Furthermore, we model the rate and distortion characteristic of NIC as a function of the coding parameter $λ$ respectively. Our experiments show our proposed method is easy to adopt and realizes state-of-the-art continuous bit-rate coding performance, which implies that our approach would benefit the practical deployment of NIC.

Zhimeng Huang, Chuanmin Jia, Shanshe Wang et al.

Optimized for pixel fidelity metrics, images compressed by existing image codec are facing systematic challenges when used for visual analysis tasks, especially under low-bitrate coding. This paper proposes a visual analysis-motivated rate-distortion model for Versatile Video Coding (VVC) intra compression. The proposed model has two major contributions, a novel rate allocation strategy and a new distortion measurement model. We first propose the region of interest for machine (ROIM) to evaluate the degree of importance for each coding tree unit (CTU) in visual analysis. Then, a novel CTU-level bit allocation model is proposed based on ROIM and the local texture characteristics of each CTU. After an in-depth analysis of multiple distortion models, a visual analysis friendly distortion criteria is subsequently proposed by extracting deep feature of each coding unit (CU). To alleviate the problem of lacking spatial context information when calculating the distortion of each CU, we finally propose a multi-scale feature distortion (MSFD) metric using different neighboring pixels by weighting the extracted deep features in each scale. Extensive experimental results show that the proposed scheme could achieve up to 28.17\% bitrate saving under the same analysis performance among several typical visual analysis tasks such as image classification, object detection, and semantic segmentation.