The Devil Is in the Details: Window-based Attention for Image Compression
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Centre for Artificial Intelligence and Robotics, HKISI_CAS（中国科学院香港创新研究院人工智能与机器人创新中心）
Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are based on Convolutional Neural Networks (CNNs). Despite great contributions, a main drawback of CNN based model is that its structure is not designed for capturing local redundancy, especially the non-repetitive textures, which severely affects the reconstruction quality. Therefore, how to make full use of both global structure and local texture becomes the core problem for learning-based image compression. Inspired by recent progresses of Vision Transformer (ViT) and Swin Transformer, we found that combining the local-aware attention mechanism with the global-related feature learning could meet the expectation in image compression. In this paper, we first extensively study the effects of multiple kinds of attention mechanisms for local features learning, then introduce a more straightforward yet effective window-based local attention block. The proposed window-based attention is very flexible which could work as a plug-and-play component to enhance CNN and Transformer models. Moreover, we propose a novel Symmetrical TransFormer (STF) framework with absolute transformer blocks in the down-sampling encoder and up-sampling decoder. Extensive experimental evaluations have shown that the proposed method is effective and outperforms the state-of-the-art methods. The code is publicly available at https://github.com/Googolxx/STF.
MambaIC: State Space Models for High-Performance Learned Image Compression
Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学）；School of Computer Science, Peking University（北京大学计算机学院）；University of Science and Technology Beijing（北京科技大学）；UCAS-Terminus AI Lab, University of Chinese Academy of Sciences（中国科学院大学Terminus AI实验室，中国科学院大学）
OMR-NET: a two-stage octave multi-scale residual network for screen content image compression
School of software, Shandong University（山东大学软件学院）；School of information science and engineering, Shandong University（山东大学信息科学与工程学院）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）
Image compression is an important filed in image processing. The science welcomes any tinny contribution that may increase the compression ratio by whichever insignificant percentage. Therefore, the essential contribution in this paper is to increase the compression ratio for the well known Portable Network Graphics (PNG) image file format. The contribution starts with converting the original PNG image into k-Modulus Method (k-MM). Practically, taking k equals to ten, and then the pixels in the constructed image will be integers divisible by ten. Since PNG uses Lempel-Ziv compression algorithm…
Spectral and Spatial Graph Learning for Multispectral Solar Image Compression
Department of Computer Science and Electrical Engineering, West Virginia University, WV, USA（计算机科学与电气工程系，维珍尼亚大学）；Department of Mechanical & Aerospace Engineering, West Virginia University, WV, USA（机械与航空航天工程系，维珍尼亚大学）；NASA Goddard Space Flight Center, MD, USA（国家航空航天局戈达德空间飞行中心）
ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression
Electrical and Computer Engineering Department, The University of British Columbia（英属哥伦比亚大学电气与计算机工程系）；School of Engineering Science, Simon Fraser University（西蒙弗雷泽大学工程科学学院）；School of Electronic Science and Technology, Eastern Institute of Technology（电子科学与技术学院，东部技术学院）；Google LLC（谷歌公司）
