CPIPS: Learning to Preserve Perceptual Distances in End-to-End Image Compression

2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC(2023)

引用 0|浏览4
暂无评分
摘要
Lossy image coding standards such as JPEG and MPEG have successfully achieved high compression rates for human consumption of multimedia data. However, with the increasing prevalence of IoT devices, drones, and self-driving cars, machines rather than humans are processing a greater portion of captured visual content. Consequently, it is crucial to pursue an efficient compressed representation that caters not only to human vision but also to image processing and machine vision tasks. Drawing inspiration from the efficient coding hypothesis in biological systems and the modeling of the sensory cortex in neural science, we repurpose the compressed latent representation to prioritize semantic relevance while preserving perceptual distance. Our proposed method, Compressed Perceptual Image Patch Similarity (CPIPS), can be derived at a minimal cost from a learned neural codec and computed significantly faster than DNN-based perceptual metrics such as LPIPS and DISTS.
更多
查看译文
关键词
End-to-end learned compression,image quality assessment,perceptual distance,coding for machines
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要