Diffusion probabilistic models have recently achieved remarkable success in generating high quality image and video data. In this work, we build on this class of generative models and introduce a method for lossy compression of high resolution images. The resulting codec, which we call DIffuson-based Residual Augmentation Codec (DIRAC), is the first neural codec to allow smooth traversal of the rate-distortion-perception tradeoff at test time, while obtaining competitive performance with GAN-based methods in perceptual quality. Furthermore, while sampling from diffusion probabilistic models is notoriously expensive, we show that in the compression setting the number of steps can be drastically reduced.
Generative Neural Video Compression via Video Diffusion Prior
School of Information and Communication Engineering, Communication University of China（信息与通信工程学院，通信大学）；School of Computer Science, Peking University（计算机学院，北京大学）
Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；School of Vehicle and Mobility, Tsinghua University（清华大学车辆与 mobility学院）
Institute for AI Industry Research, Tsinghua University（清华人工智能产业研究院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；Harbin Institute of Technology（哈尔滨工业大学）；Hong Kong University of Science and Technology（香港科技大学）；University of Chinese Academy of Sciences（中国科学院大学）
We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame is inverted in the latent space of StyleGAN, from which the optimal compression is learned. To do so, a diffeomorphic latent representation is learned using a normalizing flows model, where an entropy model can be optimized for image coding. In addition, we propose a new perceptual loss that is more efficient than other counterparts. Finally, an entropy model for video inter coding…
Cornell University（康奈尔大学）；Delft University of Technology（代尔夫特理工大学）
A common strategy for improving model robustness is through data augmentations. Data augmentations encourage models to learn desired invariances, such as invariance to horizontal flipping or small changes in color. Recent work has shown that arbitrary style transfer can be used as a form of data augmentation to encourage invariance to textures by creating painting-like images from photographs. However, a stylized photograph is not quite the same as an artist-created painting. Artists depict perceptually meaningful cues in paintings so that humans can recognize salient components in scenes, an …
Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）
Semantic communications has received growing interest since it can remarkably reduce the amount of data to be transmitted without missing critical information. Most existing works explore the semantic encoding and transmission for text and apply techniques in Natural Language Processing (NLP) to interpret the meaning of the text. In this paper, we conceive the semantic communications for image data that is much more richer in semantics and bandwidth sensitive. We propose an reinforcement learning based adaptive semantic coding (RL-ASC) approach that encodes images beyond pixel level. Firstly, …
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Netflix Inc.（奈飞公司）
Block based motion estimation is integral to inter prediction processes performed in hybrid video codecs. Prevalent block matching based methods that are used to compute block motion vectors (MVs) rely on computationally intensive search procedures. They also suffer from the aperture problem, which can worsen as the block size is reduced. Moreover, the block matching criteria used in typical codecs do not account for the resulting levels of perceptual quality of the motion compensated pictures that are created upon decoding. Towards achieving the elusive goal of perceptually optimized motion e…
Several deep learned lossy compression techniques have been proposed in the recent literature. Most of these are optimized by using either MS-SSIM (multi-scale structural similarity) or MSE (mean squared error) as a loss function. Unfortunately, neither of these correlate well with human perception and this is clearly visible from the resulting compressed images. In several cases, the MS-SSIM for deep learned techniques is higher than say a conventional, non-deep learned codec such as JPEG-2000 or BPG. However, the images produced by these deep learned techniques are in many cases clearly wors…
FDIM: A Feature-distance-based Generic Video Quality Metric for Versatile Codecs
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；Zhejiang Key Laboratory of Multimodal Communication Networks and Intelligent Information Processing（浙江省多模态通信网络与智能信息处理重点实验室）；Central Media Technology Institute, Huawei（华为中央媒体技术研究所）
VoxelCloud Inc（体素科技公司）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Shanghai Jiao Tong University（上海交通大学）
Deep learning models tend to underperform in the presence of domain shifts. Domain transfer has recently emerged as a promising approach wherein images exhibiting a domain shift are transformed into other domains for augmentation or adaptation. However, with the absence of paired and annotated images, models merely learned by adversarial loss and cycle consistency loss could result in poor consistency of anatomy structures during the translation. Additionally, the complexity of learning multi-domain transfer could significantly increase with the number of target domains and source images. In t…
Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment
Image Processing Lab, Universidad de Valencia（瓦伦西亚大学图像处理实验室）；Center for Biomaterials and Tissue Engineering Universitat Politecnica de Valencia（多尔多涅理工大学生物材料与组织工程中心）
JPEG AIC2026: A large-scale dataset for fine-grained assessment of image coding
University of Konstanz（康斯坦茨大学）；Cloudinary（Cloudinary公司）；IST-IT（IST-IT机构）；Fraunhofer IIS（弗劳恩霍夫应用固体物理研究所）；Huawei（华为公司）；Takushoku University（拓殖大学）；IT-UBI（IT-UBI机构）；EPFL（洛桑联邦理工学院）
Invariance to a broad array of image corruptions, such as warping, noise, or color shifts, is an important aspect of building robust models in computer vision. Recently, several new data augmentations have been proposed that significantly improve performance on ImageNet-C, a benchmark of such corruptions. However, there is still a lack of basic understanding on the relationship between data augmentations and test-time corruptions. To this end, we develop a feature space for image transforms, and then use a new measure in this space between augmentations and corruptions called the Minimal Sampl…
Recent years have witnessed the dramatic growth of Internet video traffic, where the video bitstreams are often compressed and delivered in low quality to fit the streamer's uplink bandwidth. To alleviate the quality degradation, it comes the rise of Neural-enhanced Video Streaming (NVS), which shows great prospects for recovering low-quality videos by mostly deploying neural super-resolution (SR) on the media server. Despite its benefit, we reveal that current mainstream works with SR enhancement have not achieved the desired rate-distortion trade-off between bitrate saving and quality restor…
GFix: Perceptually Enhanced Gaussian Splatting Video Compression
Visual Information Laboratory, University of Bristol（布里斯托大学视觉信息实验室）；University of Bristol（布里斯托大学）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）；Visionular Inc.（Visionular公司）
RBFIM: Perceptual Quality Assessment for Compressed Point Clouds Using Radial Basis Function Interpolation
School of Electronics and Information, Northwestern Polytechnical University（电子与信息学院，西北工业大学）；School of Engineering, Royal Melbourne Institute of Technology（工程学院，皇家墨尔本理工学院）；Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）；School of Telecommunication Engineering, Xidian University（电信工程学院，西安电子科技大学）
Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling
National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（北京大学计算机学院视觉技术国家工程研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Peng Cheng Laboratory（鹏城实验室）
We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual similarity term between generated and real images (ii) incorporating several techniques from the adversarial training literature including multi-scale training and adaptive discriminator augmentation. The combination of these results in not only better pixel reconstruction but also representations which appear to capture better higher-level details within images. …
