Recent studies in extreme image compression have achieved remarkable performance by compressing the tokens from generative tokenizers. However, these methods often prioritize clustering common semantics within the dataset, while overlooking the diverse details of individual objects. Consequently, this results in suboptimal reconstruction fidelity, especially at low bitrates. To address this issue, we introduce a Dual-generative Latent Fusion (DLF) paradigm. DLF decomposes the latent into semantic and detail elements, compressing them through two distinct branches. The semantic branch clusters high-level information into compact tokens, while the detail branch encodes perceptually critical details to enhance the overall fidelity. Additionally, we propose a cross-branch interactive design to reduce redundancy between the two branches, thereby minimizing the overall bit cost. Experimental results demonstrate the impressive reconstruction quality of DLF even below 0.01 bits per pixel (bpp). On the CLIC2020 test set, our method achieves bitrate savings of up to 27.93% on LPIPS and 53.55% on DISTS compared to MS-ILLM. Furthermore, DLF surpasses recent diffusion-based codecs in visual fidelity while maintaining a comparable level of generative realism. Project: https://dlfcodec.github.io/
Given an grayscale digital image, and a positive integer $n$, how well can we store the image at a compression ratio of $n:1$? In this paper we address the above question in extreme cases when $n>>50$ using "$\mathbf{V}$-variable image compression".
Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior
China Telecom Group Corporation-Xi’an Jiaotong University Jointly Established Intelligent Cloud Network Science and Education Integration Innovation Research Institute（中国电信集团有限公司-西安交通大学联合成立的智能云网科教融合创新研究院）
RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（人工智能与机器人研究所，西安交通大学）；Department of Computer Science and Software Engineering, The University of Western Australia（计算机科学与软件工程系，西澳大学）
Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compression
School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（上海交通大学信息科学与电子工程学院）；Department of Electronic Engineer and Information Science, University of Science and Technology of China（中国科学技术大学电子工程与信息科学系）；MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能教育部重点实验室）
University of Essex（埃塞克斯大学）；Queensland University of Technology（昆士兰科技大学）；University of Southampton（南安普顿大学）
Visual Place Recognition (VPR) is the ability of a robotic platform to correctly interpret visual stimuli from its on-board cameras in order to determine whether it is currently located in a previously visited place, despite different viewpoint, illumination and appearance changes. JPEG is a widely used image compression standard that is capable of significantly reducing the size of an image at the cost of image clarity. For applications where several robotic platforms are simultaneously deployed, the visual data gathered must be transmitted remotely between each robot. Hence, JPEG compression…
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough investigation of the architecture design of learned image compression, regarding both compression performance and running speed, is essential. In this paper, we first propose uneven channel-conditional adaptive coding, motivated by the observation of energy compaction in learned image compression. Combining the proposed uneven grouping model with existing context…
A rapidly increasing portion of internet traffic is dominated by requests from mobile devices with limited and metered bandwidth constraints. To satisfy these requests, it has become standard practice for websites to transmit small and extremely compressed image previews as part of the initial page load process to improve responsiveness. Increasing thumbnail compression beyond the capabilities of existing codecs is therefore an active research direction. In this work, we concentrate on extreme compression rates, where the size of the image is typically 200 bytes or less. First, we propose a no…
Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（人机混合增强智能国家重点实验室，人工智能与机器人研究院，西安交通大学）；School of Information and Telecommunication, Xi’an Jiaotong University（信息与电信学院，西安交通大学）；Department of Computer Science and Software Engineering, The University of Western Australia（计算机科学与软件工程系，西澳大学）
Dartmouth College（达特茅斯学院）；Disney Research LA（迪士尼研究院洛杉矶）；DisneyResearch|Studios（迪士尼研究工作室）；University of California, Irvine（加州大学欧文分校）
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling approach to compress temporal sequences with a focus on video. Our approach builds upon variational autoencoder (VAE) models for sequential data and combines them with recent work on neural image compression. The approach jointly learns to transform the original sequence into a lower-dimensional representation as well as to discretize and entropy code this represen…
Segmentation-based image coding methods provide high compression ratios when compared with traditional image coding approaches like the transform and sub band coding for low bit-rate compression applications. In this paper, a segmentation-based image coding method, namely the Binary Space Partition scheme, that divides the desired image using a recursive procedure for coding is presented. The BSP approach partitions the desired image recursively by using bisecting lines, selected from a collection of discrete optional lines, in a hierarchical manner. This partitioning procedure generates a bin…
Lossy compression algorithms aim to compactly encode images in a way which enables to restore them with minimal error. We show that a key limitation of existing algorithms is that they rely on error measures that are extremely sensitive to geometric deformations (e.g. SSD, SSIM). These force the encoder to invest many bits in describing the exact geometry of every fine detail in the image, which is obviously wasteful, because the human visual system is indifferent to small local translations. Motivated by this observation, we propose a deformation-insensitive error measure that can be easily i…
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…
Compressing images at extremely low bitrates (< 0.1 bpp) has always been a challenging task since the quality of reconstruction significantly reduces due to the strong imposed constraint on the number of bits allocated for the compressed data. With the increasing need to transfer large amounts of images with limited bandwidth, compressing images to very low sizes is a crucial task. However, the existing methods are not effective at extremely low bitrates. To address this need, we propose a novel network called CompressNet which augments a Stacked Autoencoder with a Switch Prediction Network (S…
Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China（多媒体信息处理国家重点实验室，计算机科学学院，北京大学，北京，中国）；State Key Discipline Laboratory of Wide Band-Gap Semiconductor Technology, School of Microelectronics, Xidian University, Xi'an, China（宽带隙半导体技术重点学科实验室，微电子学院，西安电子科技大学，西安，中国）
We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned compression objective. The model synthesizes details it cannot afford to store, obtaining visually pleasing results at bitrates where previous methods fail and show strong artifacts. Furthermore, if a semantic label map of the original image is available, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from…
ExGS: Extreme 3D Gaussian Compression with Diffusion Priors
Northwestern Polytechnical University（北western工业大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Hong Kong University of Science and Technology（香港科技大学）
Linear Algebraic Approaches to Neuroimaging Data Compression: A Comparative Analysis of Matrix and Tensor Decomposition Methods for High-Dimensional Medical Images
In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation. Unlike other low-rank decomposition algorithms which operate on spatial or channel dimension of filters, our proposed method mainly focuses on exploiting the filter group structure for each layer. For several commonly used CNN models, including VGG and ResNet, our method can reduce over 80% floating-point operations (FLOPs) with less accuracy drop than state…
We introduce an efficient method for the reconstruction of the correlation between a compressively measured image and a phase-only filter. The proposed method is based on two properties of phase-only filtering: such filtering is a unitary circulant transform, and the correlation plane it produces is usually sparse. Thanks to these properties, phase-only filters are perfectly compatible with the framework of compressive sensing. Moreover, the lasso-based recovery algorithm is very fast when phase-only filtering is used as the compression matrix. The proposed method can be seen as a generalisati…
Extreme Model Compression for Edge Vision-Language Models: Sparse Temporal Token Fusion and Adaptive Neural Compression
University of Information Technology and Sciences（信息科技与科学大学）；The University of Burdwan（布尔德万大学）；Tarakeswar Degree College（塔拉克瓦尔学位学院）；University of Missouri, Columbia（密苏里大学，哥伦比亚）
University of Maryland, College Park（马里兰大学帕克分校）；Google Research（谷歌研究院）
We introduce LilNetX, an end-to-end trainable technique for neural networks that enables learning models with specified accuracy-rate-computation trade-off. Prior works approach these problems one at a time and often require post-processing or multistage training which become less practical and do not scale very well for large datasets or architectures. Our method constructs a joint training objective that penalizes the self-information of network parameters in a reparameterized latent space to encourage small model size while also introducing priors to increase structured sparsity in the para…
Spatiotemporally adaptive compression for scientific dataset with feature preservation -- a case study on simulation data with extreme climate events analysis
Oak Ridge National Laboratory（橡树岭国家实验室）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；University of Kentucky（肯塔基大学）；University of Alabama（阿拉巴马大学）；University of Florida（佛罗里达大学）；Georgia State University（佐治亚州立大学）；Argonne National Laboratory（阿贡国家实验室）
Spectral Complex Autoencoder Pruning: A Fidelity-Guided Criterion for Extreme Structured Channel Compression
School of Computer, Jiangsu University of Science and Technology（江苏科技大学计算机学院）；Department of Electrical and Computer Engineering, University of Nevada, Las Vegas（内华达大学拉斯维加斯分校电子与计算机工程系）
