PO-ELIC: Perception-Oriented Efficient Learned Image Coding

He, Dailan; Yang, Ziming; Hou, Yu; Xu, Tongda; Luo, Jixiang; Chen, Yuan; Gao, Chenjian; Shi, Xinjie; Qin, Hongwei; Wang, Yan

doi:10.1109/cvprw56347.2022.00187

“…Given that a universal objective quality metric remains undiscovered, we see a surge in research that considers the realism of the reconstructed image for better subjective quality [134][135][136][137].…”

Section: Subjective Image Qualitymentioning

confidence: 99%

Unveiling the Future of Human and Machine Coding: A Survey of End-to-End Learned Image Compression

Huang,

Wu

2024

Entropy

0

View full text Add to dashboard Cite

End-to-end learned image compression codecs have notably emerged in recent years. These codecs have demonstrated superiority over conventional methods, showcasing remarkable flexibility and adaptability across diverse data domains while supporting new distortion losses. Despite challenges such as computational complexity, learned image compression methods inherently align with learning-based data processing and analytic pipelines due to their well-suited internal representations. The concept of Video Coding for Machines has garnered significant attention from both academic researchers and industry practitioners. This concept reflects the growing need to integrate data compression with computer vision applications. In light of these developments, we present a comprehensive survey and review of lossy image compression methods. Additionally, we provide a concise overview of two prominent international standards, MPEG Video Coding for Machines and JPEG AI. These standards are designed to bridge the gap between data compression and computer vision, catering to practical industry use cases.

show abstract

“…Given that a universal objective quality metric remains undiscovered, we see a surge of research that considers the realism of the reconstructed image for better subjective quality [134][135][136][137].…”

Section: Subjective Image Qualitymentioning

confidence: 99%

Unveiling the Future of Human and Machine Coding: A Survey of End-to-End Learned Image Compression

Huang,

Wu

2024

Preprint

0

View full text Add to dashboard Cite

End-to-end learned image compression codecs have notably emerged in recent years. These codecs have demonstrated superiority over conventional methods, showcasing remarkable flexibility and adaptability across diverse data domains while supporting new distortion losses. Despite challenges such as computational complexity, learned image compression methods inherently align with learning-based data processing and analytic pipelines due to their well-suited internal representations. The concept of Video Coding for Machines has garnered significant attention from both academic researchers and industry practitioners. This concept reflects the growing need to integrate data compression with computer vision applications. In light of these developments, we present a comprehensive survey and review of lossy image compression methods. Additionally, we provide a concise overview of two prominent international standards, MPEG Video Coding for Machines and JPEG AI. These standards are designed to bridge the gap between data compression and computer vision, catering to practical industry use cases.

show abstract

“…A slightly different line of research aims at the realism of image reconstruction in addition to the objective of ratedistortion optimisation. This is most commonly achieved by GANs [38,2,26,13,18] but also by other generative models such as denoising diffusion [35,14].…”

Section: Related Workmentioning

confidence: 99%

SASIC: Stereo Image Compression with Latent Shifts and Stereo Attention

Wödlinger

¹

,

Kotera

²

,

Xu³

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

In this paper, we present ECSIC, a novel learned method for stereo image compression. Our proposed method compresses the left and right images in a joint manner by exploiting the mutual information between the images of the stereo image pair using a novel stereo cross attention (SCA) module and two stereo context modules. The SCA module performs cross-attention restricted to the corresponding epipolar lines of the two images and processes them in parallel. The stereo context modules improve the entropy estimation of the second encoded image by using the first image as a context. We conduct an extensive ablation study demonstrating the effectiveness of the proposed modules and a comprehensive quantitative and qualitative comparison with existing methods. ECSIC achieves state-of-theart performance among stereo image compression models on the two popular stereo image datasets Cityscapes and InStereo2k while allowing for fast encoding and decoding, making it highly practical for real-time applications.

show abstract

PO-ELIC: Perception-Oriented Efficient Learned Image Coding

Cited by 15 publications

References 15 publications

Unveiling the Future of Human and Machine Coding: A Survey of End-to-End Learned Image Compression

Unveiling the Future of Human and Machine Coding: A Survey of End-to-End Learned Image Compression

Unveiling the Future of Human and Machine Coding: A Survey of End-to-End Learned Image Compression

SASIC: Stereo Image Compression with Latent Shifts and Stereo Attention

Contact Info

Product

Resources

About