Mean squared error (MSE) and $\ell_p$ norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess visual information loss, these simple norms are not highly consistent with human perception. Here, we propose a different proxy approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, which mimics the perceptual model while serving as a loss layer of the network.We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of a modern deep image compression models, we are able to demonstrate an averaged bitrate reduction of $28.7\%$ over MSE optimization, given a specified perceptual quality (VMAF) level.
Center for Machine Perception, Czech Technical University（捷克技术大学机器感知中心）；Amazon（亚马逊）
Recently, there has been much interest in deep learning techniques to do image compression and there have been claims that several of these produce better results than engineered compression schemes (such as JPEG, JPEG2000 or BPG). A standard way of comparing image compression schemes today is to use perceptual similarity metrics such as PSNR or MS-SSIM (multi-scale structural similarity). This has led to some deep learning techniques which directly optimize for MS-SSIM by choosing it as a loss function. While this leads to a higher MS-SSIM for such techniques, we demonstrate using user studie…
We propose a deep learning system for attention-guided dual-layer image compression (AGDL). In the AGDL compression system, an image is encoded into two layers, a base layer and an attention-guided refinement layer. Unlike the existing ROI image compression methods that spend an extra bit budget equally on all pixels in ROI, AGDL employs a CNN module to predict those pixels on and near a saliency sketch within ROI that are critical to perceptual quality. Only the critical pixels are further sampled by compressive sensing (CS) to form a very compact refinement layer. Another novel CNN method is…
Spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency. This approach encodes a lower resolution version of the input video and reconstructs the original resolution during decoding. Instead of using conventional up-sampling filters, recent work has employed advanced super-resolution methods based on convolutional neural networks (CNNs) to further improve reconstruction quality. These approaches are usually trained to minimise pixel-based losses such as Mean-Squared Error (MSE), despite the fact that this type of loss metric …
The Hong Kong Univeristy of Science and Technology（香港科技大学）
High levels of noise usually exist in today's captured images due to the relatively small sensors equipped in the smartphone cameras, where the noise brings extra challenges to lossy image compression algorithms. Without the capacity to tell the difference between image details and noise, general image compression methods allocate additional bits to explicitly store the undesired image noise during compression and restore the unpleasant noisy image during decompression. Based on the observations, we optimize the image compression algorithm to be noise-aware as joint denoising and compression t…
We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator and discriminator architectures, training strategies, as well as perceptual losses. In contrast to previous work, i) we obtain visually pleasing reconstructions that are perceptually similar to the input, ii) we operate in a broad range of bitrates, and iii) our approach can be applied to high-resolution images. We bridge the gap between rate-distortion-perception theory and pr…
In many professional fields, such as medicine, remote sensing and sciences, users often demand image compression methods to be mathematically lossless. But lossless image coding has a rather low compression ratio (around 2:1 for natural images). The only known technique to achieve significant compression while meeting the stringent fidelity requirements is the methodology of $\ell_\infty$-constrained coding that was developed and standardized in nineties. We make a major progress in $\ell_\infty$-constrained image coding after two decades, by developing a novel CNN-based soft $\ell_\infty$-con…
University of Science and Technology of China（中国科学技术大学）；City University of Hong Kong（香港城市大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
Although equirectangular projection (ERP) is a convenient form to store omnidirectional images (also known as 360-degree images), it is neither equal-area nor conformal, thus not friendly to subsequent visual communication. In the context of image compression, ERP will over-sample and deform things and stuff near the poles, making it difficult for perceptually optimal bit allocation. In conventional 360-degree image compression, techniques such as region-wise packing and tiled representation are introduced to alleviate the over-sampling problem, achieving limited success. In this paper, we mak…
In recent years, resolution adaptation based on deep neural networks has enabled significant performance gains for conventional (2D) video codecs. This paper investigates the effectiveness of spatial resolution resampling in the context of immersive content. The proposed approach reduces the spatial resolution of input multi-view videos before encoding, and reconstructs their original resolution after decoding. During the up-sampling process, an advanced CNN model is used to reduce potential re-sampling, compression, and synthesis artifacts. This work has been fully tested with the TMIV coding…
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…
Waseda University（早稻田大学）；Waseda Research Institute for Science and Engineering（早稻田大学科学与工程研究院）
Learned image compression allows achieving state-of-the-art accuracy and compression ratios, but their relatively slow runtime performance limits their usage. While previous attempts on optimizing learned image codecs focused more on the neural model and entropy coding, we present an alternative method to improving the runtime performance of various learned image compression models. We introduce multi-threaded pipelining and an optimized memory model to enable GPU and CPU workloads asynchronous execution, fully taking advantage of computational resources. Our architecture alone already produce…
Image similarity measurement is a common issue in a broad range of applications in image processing, recognition, classification and retrieval. Conventional image similarity measures are often limited to specific applications and cannot be applied in general scenarios. The theory of Kolmogorov complexity provides a universal framework for a generic similarity metric based on information distance between objects. Normalized Information Distance (NID) has been shown to be a valid and universal distance metric applicable in measurement of similarity of any two objects, and has been successfully a…
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）
Ultra high resolution (UHR) images are almost always downsampled to fit small displays of mobile end devices and upsampled to its original resolution when exhibited on very high-resolution displays. This observation motivates us on jointly optimizing operation pairs of downsampling and upsampling that are spatially adaptive to image contents for maximal rate-distortion performance. In this paper, we propose an adaptive downsampled dual-layer (ADDL) image compression system. In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and co…
In recent years, with the development of deep neural networks, end-to-end optimized image compression has made significant progress and exceeded the classic methods in terms of rate-distortion performance. However, most learning-based image compression methods are unlabeled and do not consider image semantics or content when optimizing the model. In fact, human eyes have different sensitivities to different content, so the image content also needs to be considered. In this paper, we propose a content-oriented image compression method, which handles different kinds of image contents with differ…
T-MLA: A targeted multiscale log-exponential attack framework for neural image compression
Skolkovo Institute of Science and Technology（斯克尔科沃科学与技术研究所）；University of Electronic Science and Technology of China（电子科学与技术大学）；Artificial Intelligence Research Institute (AIRI)（人工智能研究 institute (AIRI)）
ETH Zurich（苏黎世联邦理工学院）；Technical University of Munich（慕尼黑工业大学）；Google（谷歌）
Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Thus far, prior work mostly focused on optimizing their reconstruction performance. This work investigates INRs from a novel perspective, i.e., as a tool for image compression. To this end, we propose the first comprehensive compression pipeline based on INRs including quantization, quantization-aware retraining and entropy coding. Encoding with INRs, i.e. overfitting to a data sample, is typically orders of magnitude slower. To mitigate this drawback, we leverage me…
To provide users with more realistic visual experiences, videos are developing in the trends of Ultra High Definition (UHD), High Frame Rate (HFR), High Dynamic Range (HDR), Wide Color Gammut (WCG) and high clarity. However, the data amount of videos increases exponentially, which requires high efficiency video compression for storage and network transmission. Perceptually optimized video coding aims to maximize compression efficiency by exploiting visual redundancies. In this paper, we present a broad and systematic survey on perceptually optimized video coding. Firstly, we present problem fo…
We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms which are more flexible than existing codecs. Autoencoders have the potential to address this need, but are difficult to optimize directly due to the inherent non-differentiabilty of the compression loss. We here show that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approac…
By optimizing the rate-distortion-realism trade-off, generative compression approaches produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions produced by rate-distortion optimized models. However, previous methods do not explicitly control how much detail is synthesized, which results in a common criticism of these methods: users might be worried that a misleading reconstruction far from the input image is generated. In this work, we alleviate these concerns by training a decoder that can bridge the two regimes and navigate the distortion-realism trade…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
The emerging and existing light field displays are highly capable of realistic presentation of 3D scenes on auto-stereoscopic glasses-free platforms. The light field size is a major drawback while utilising 3D displays and streaming purposes. When a light field is of high dynamic range, the size increases drastically. In this paper, we propose a novel compression algorithm for a high dynamic range light field which yields a perceptually lossless compression. The algorithm exploits the inter and intra view correlations of the HDR light field by interpreting it to be a four-dimension volume. The…
Institute of Informatics & Telecommunications, NCSR Demokritos（希腊国家科学研究中心德谟克利特信息学与电信研究所）；Information Management Systems Institute, Athena Research Center（雅典娜研究中心信息管理系统研究所）；University of Piraeus（比雷埃夫斯大学）
In previous work we introduced a trajectory detection module that can provide summarized representations of vessel trajectories by consuming AIS positional messages online. This methodology can provide reliable trajectory synopses with little deviations from the original course by discarding at least 70% of the raw data as redundant. However, such trajectory compression is very sensitive to parametrization. In this paper, our goal is to fine-tune the selection of these parameter values. We take into account the type of each vessel in order to provide a suitable configuration that can yield imp…
In image and video coding applications, distortion has been traditionally measured using mean square error (MSE), which suggests the use of orthogonal transforms, such as the discrete cosine transform (DCT). Perceptual metrics such as Structural Similarity (SSIM) are typically used after encoding, but not tied to the encoding process. In this paper, we consider an alternative framework where the goal is to optimize a weighted MSE metric, where different weights can be assigned to each pixel so as to reflect their relative importance in terms of perceptual image quality. For this purpose, we pr…
Transferring large amount of high resolution images over limited bandwidth is an important but very challenging task. Compressing images using extremely low bitrates (<0.1 bpp) has been studied but it often results in low quality images of heavy artifacts due to the strong constraint in the number of bits available for the compressed data. It is often said that a picture is worth a thousand words but on the other hand, language is very powerful in capturing the essence of an image using short descriptions. With the recent success of diffusion models for text-to-image generation, we propose a g…
Due to the spectral sensitivity phenomenon of the Human Visual System (HVS), the color channels of raw RGB 4:4:4 sequences contain significant psychovisual redundancies; these redundancies can be perceptually quantized. The default quantization systems in the HEVC standard are known as Uniform Reconstruction Quantization (URQ) and Rate Distortion Optimized Quantization (RDOQ); URQ and RDOQ are not perceptually optimized for the coding of RGB 4:4:4 video data. In this paper, we propose a novel spatiotemporal perceptual quantization technique named SPAQ. With application for RGB 4:4:4 video data…
In perceptual image coding applications, the main objective is to decrease, as much as possible, Bits Per Pixel (BPP) while avoiding noticeable distortions in the reconstructed image. In this paper, we propose a novel perceptual image coding technique, named Perceptual Color Compression (PCC). PCC is based on a novel model related to Human Visual System (HVS) spectral sensitivity and CIELAB Just Noticeable Color Difference (JNCD). We utilize this modeling to capitalize on the inability of the HVS to perceptually differentiate photons in very similar wavelength bands (e.g., distinguishing very …
Deep learning for computer vision depends on lossy image compression: it reduces the storage required for training and test data and lowers transfer costs in deployment. Mainstream datasets and imaging pipelines all rely on standard JPEG compression. In JPEG, the degree of quantization of frequency coefficients controls the lossiness: an 8 by 8 quantization table (Q-table) decides both the quality of the encoded image and the compression ratio. While a long history of work has sought better Q-tables, existing work either seeks to minimize image distortion or to optimize for models of the human…
In this paper, we propose a novel end-to-end feature compression scheme by leveraging the representation and learning capability of deep neural networks, towards intelligent front-end equipped analysis with promising accuracy and efficiency. In particular, the extracted features are compactly coded in an end-to-end manner by optimizing the rate-distortion cost to achieve feature-in-feature representation. In order to further improve the compression performance, we present a latent code level teacher-student enhancement model, which could efficiently transfer the low bit-rate representation int…
Human perception is at the core of lossy video compression and yet, it is challenging to collect data that is sufficiently dense to drive compression. In perceptual quality assessment, human feedback is typically collected as a single scalar quality score indicating preference of one distorted video over another. In reality, some videos may be better in some parts but not in others. We propose an approach to collecting finer-grained feedback by asking users to use an interactive tool to directly optimize for perceptual quality given a fixed bitrate. To this end, we built a novel web-tool which…
School of Computing Science, University of Glasgow（格拉斯哥大学计算科学学院）
There is a proliferation in the number of satellites launched each year, resulting in downlinking of terabytes of data each day. The data received by ground stations is often unprocessed, making this an expensive process considering the large data sizes and that not all of the data is useful. This, coupled with the increasing demand for real-time data processing, has led to a growing need for on-orbit processing solutions. In this work, we investigate the performance of CNN-based object detectors on constrained devices by applying different image compression techniques to satellite data. We ex…
ROIX-Comp: Optimizing X-ray Computed Tomography Imaging Strategy for Data Reduction and Reconstruction
The University of Electro-Communications, RIKEN (R-CCS)（电子通信大学，RIKEN（R-CCS））；Japan Synchrotron Radiation Research Institute（日本同步辐射研究中心）；RIKEN SPring-8 Center（RIKEN SPring-8研究中心）
Xidian University（西安电子科技大学）；BBC Research & Development（英国广播公司研发中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Northwestern Polytechnical University（西北工业大学）
Recent years have witnessed the significant development of learning-based video compression methods, which aim at optimizing objective or perceptual quality and bit rates. In this paper, we introduce deep video compression with perceptual optimizations (DVC-P), which aims at increasing perceptual quality of decoded videos. Our proposed DVC-P is based on Deep Video Compression (DVC) network, but improves it with perceptual optimizations. Specifically, a discriminator network and a mixed loss are employed to help our network trade off among distortion, perception and rate. Furthermore, nearest-n…
Image compression with upsampling encodes information to succeedingly increase image resolution, for example by encoding differences in FUIF and JPEG XL. It is useful for progressive decoding, also often can improve compression ratio - both for lossless compression and e.g. DC coefficients of lossy. However, the currently used solutions rather do not exploit context dependence for encoding of such upscaling information. This article discusses simple inexpensive general techniques for this purpose, which allowed to save on average $0.645$ bits/difference (between $0.138$ and $1.489$) for the la…
