Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Haichao, Wen, Jiangtao, Han, Yuxing
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.05990
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909901360463872
author Wang, Haichao
Wen, Jiangtao
Han, Yuxing
author_facet Wang, Haichao
Wen, Jiangtao
Han, Yuxing
contents Video computer vision systems face substantial computational burdens arising from two fundamental challenges: eliminating unnecessary processing and reducing temporal redundancy in back-end inference while maintaining accuracy with minimal extra computation. To address these issues, we propose an efficient video computer vision framework that jointly optimizes both the front end and back end of the pipeline. On the front end, we remove the traditional image signal processor (ISP) and feed Bayer raw measurements directly into Bayer-domain vision models, avoiding costly human-oriented ISP operations. On the back end, we introduce a fast and highly parallel motion estimation algorithm that extracts inter-frame temporal correspondence to avoid redundant computation. To mitigate artifacts caused by motion inaccuracies, we further employ lightweight perception residual networks that directly learn perception-level residuals and refine the propagated features. Experiments across multiple models and tasks demonstrate that our system achieves substantial acceleration with only minor performance degradation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05990
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Bayer-Domain Video Computer Vision with Fast Motion Estimation and Learned Perception Residual
Wang, Haichao
Wen, Jiangtao
Han, Yuxing
Computer Vision and Pattern Recognition
Video computer vision systems face substantial computational burdens arising from two fundamental challenges: eliminating unnecessary processing and reducing temporal redundancy in back-end inference while maintaining accuracy with minimal extra computation. To address these issues, we propose an efficient video computer vision framework that jointly optimizes both the front end and back end of the pipeline. On the front end, we remove the traditional image signal processor (ISP) and feed Bayer raw measurements directly into Bayer-domain vision models, avoiding costly human-oriented ISP operations. On the back end, we introduce a fast and highly parallel motion estimation algorithm that extracts inter-frame temporal correspondence to avoid redundant computation. To mitigate artifacts caused by motion inaccuracies, we further employ lightweight perception residual networks that directly learn perception-level residuals and refine the propagated features. Experiments across multiple models and tasks demonstrate that our system achieves substantial acceleration with only minor performance degradation.
title Efficient Bayer-Domain Video Computer Vision with Fast Motion Estimation and Learned Perception Residual
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.05990