中文
相关论文

相关论文: ARCHE: Autoregressive Residual Compression with Hy…

200 篇论文

We study the design of deep architectures for lossy image compression. We present two architectural recipes in the context of multi-stage progressive encoders and empirically demonstrate their importance on compression performance.…

计算机视觉与模式识别 · 计算机科学 2017-11-13 Mohammad Haris Baig , Vladlen Koltun , Lorenzo Torresani

We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core of our method is a fully parallelizable hierarchical…

图像与视频处理 · 电气工程与系统科学 2020-03-09 Fabian Mentzer , Eirikur Agustsson , Michael Tschannen , Radu Timofte , Luc Van Gool

End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts. These trainable codecs have many advantages over traditional…

图像与视频处理 · 电气工程与系统科学 2023-08-03 Muhammet Balcilar , Bharath Bhushan Damodaran , Karam Naser , Franck Galpin , Pierre Hellier

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…

图像与视频处理 · 电气工程与系统科学 2020-07-13 Li-Heng Chen , Christos G. Bampis , Zhi Li , Andrey Norkin , Alan C. Bovik

We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear…

计算机视觉与模式识别 · 计算机科学 2020-07-28 Johannes Ballé , Valero Laparra , Eero P. Simoncelli

Autoencoder-based structures have dominated recent learned image compression methods. However, the inherent information loss associated with autoencoders limits their rate-distortion performance at high bit rates and restricts their…

计算机视觉与模式识别 · 计算机科学 2025-03-31 Hanyue Tu , Siqi Wu , Li Li , Wengang Zhou , Houqiang Li

Recent research has shown a strong theoretical connection between variational autoencoders (VAEs) and the rate-distortion theory. Motivated by this, we consider the problem of lossy image compression from the perspective of generative…

图像与视频处理 · 电气工程与系统科学 2023-03-28 Zhihao Duan , Ming Lu , Zhan Ma , Fengqing Zhu

Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained image compression. Most frameworks contain static compression…

图像与视频处理 · 电气工程与系统科学 2022-01-06 Fabian Brand , Kristian Fischer , Alexander Kopte , André Kaup

Hyperdimensional Computing (HDC) is emerging as a promising approach for edge AI, offering a balance between accuracy and efficiency. However, current HDC-based applications often rely on high-precision models and/or encoding matrices to…

机器学习 · 计算机科学 2025-05-09 Nilesh Prasad Pandey , Shriniwas Kulkarni , David Wang , Onat Gungor , Flavio Ponzina , Tajana Rosing

Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Hanshuai Cui , Zhiqing Tang , Zhi Yao , Fanshuai Meng , Weijia Jia , Wei Zhao

Autoregressive models have recently shown great promise in visual generation by leveraging discrete token sequences akin to language modeling. However, existing approaches often suffer from inefficiency, either due to token-by-token…

计算机视觉与模式识别 · 计算机科学 2025-11-20 Ruiqing Yang , Kaixin Zhang , Zheng Zhang , Shan You , Tao Huang

Learned image compression has recently shown the potential to outperform the standard codecs. State-of-the-art rate-distortion (R-D) performance has been achieved by context-adaptive entropy coding approaches in which hyperprior and…

图像与视频处理 · 电气工程与系统科学 2021-01-01 Mohammad Akbari , Jie Liang , Jingning Han , Chengjie Tu

Model-based compression is an effective, facilitating, and expanded model of neural network models with limited computing and low power. However, conventional models of compression techniques utilize crafted features [2,3,12] and explore…

机器学习 · 统计学 2018-07-10 Hamed Hakkak

Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both…

图像与视频处理 · 电气工程与系统科学 2025-05-27 Zhiyuan Li , Yanhui Zhou , Hao Wei , Chenyang Ge , Ajmal Mian

Preprocessing is a well-established technique for optimizing compression, yet existing methods are predominantly Rate-Distortion (R-D) optimized and constrained by pixel-level fidelity. This work pioneers a shift towards Rate-Perception…

图像与视频处理 · 电气工程与系统科学 2025-12-18 Mengxi Guo , Shijie Zhao , Junlin Li , Li Zhang

Currently, video transmission serves not only the Human Visual System (HVS) for viewing but also machine perception for analysis. However, existing codecs are primarily optimized for pixel-domain and HVS-perception metrics rather than the…

图像与视频处理 · 电气工程与系统科学 2025-03-28 Yuxiao Sun , Yao Zhao , Meiqin Liu , Chao Yao , Weisi Lin

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…

图像与视频处理 · 电气工程与系统科学 2024-05-24 Marc Windsheimer , Fabian Brand , André Kaup

Autoregressive models for 3D mesh generation suffer from a fundamental limitation: they flatten meshes into long vertex-coordinate sequences. This results in prohibitive computational costs, hindering the efficient synthesis of…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Hanxiao Wang , Yuan-Chen Guo , Ying-Tian Liu , Zi-Xin Zou , Biao Zhang , Weize Quan , Ding Liang , Yan-Pei Cao , Dong-Ming Yan

Generative model based image lossless compression algorithms have seen a great success in improving compression ratio. However, the throughput for most of them is less than 1 MB/s even with the most advanced AI accelerated chips, preventing…

图像与视频处理 · 电气工程与系统科学 2022-06-14 Ning Kang , Shanzhao Qiu , Shifeng Zhang , Zhenguo Li , Shutao Xia

Masked autoregressive (MAR) models unify the strengths of masked and autoregressive generation by predicting tokens in a fixed order using bidirectional attention for image generation. While effective, MAR models suffer from significant…

机器学习 · 计算机科学 2025-06-17 Chaoyi Jiang , Sungwoo Kim , Lei Gao , Hossein Entezari Zarch , Won Woo Ro , Murali Annavaram