arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.01495cs.CV
收藏

ELVIS: 为暗光视频实例分割增强低光效果

ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark

Visual Information Laboratory, University of Bristol(布里斯托大学视觉信息实验室)

Joanne Lin, Ruirui Lin, Yini Li, David Bull, Nantheera Anantrasirichai

AI总结:

本文提出ELVIS框架,通过模拟低光视频管道和改进解码器,提升视频实例分割在低光条件下的性能,实验显示在合成数据集上提升3.7AP,在真实低光视频上超越基线2.8AP。

摘要:

视频实例分割(VIS)在低光内容中仍然极具挑战性,由于噪声、模糊和其他不利条件,人类和机器都面临困难。缺乏大规模标注数据集和当前合成管道的限制,特别是在建模时间退化方面,进一步阻碍了进展。此外,现有VIS方法对低光视频中发现的退化不鲁棒,因此即使经过微调后表现也较差。本文介绍ELVIS(增强低光视频实例分割),一个框架,使最先进的VIS模型能够适应低光场景。ELVIS由一个无监督的合成低光视频管道组成,该管道建模了空间和时间退化,一个无需校准的退化轮廓估计网络(VDP-Net)和一个解耦退化与内容特征的增强解码器头。ELVIS在合成低光YouTube-VIS 2019数据集上性能提升高达+3.7AP,并在真实低光视频上超越两个阶段基线至少+2.8AP。代码和数据集可在:https://joannelin168.github.io/research/ELVIS获取。

英文摘要:

Video instance segmentation (VIS) for low-light content remains highly challenging for both humans and machines alike, due to noise, blur and other adverse conditions. The lack of large-scale annotated datasets and the limitations of current synthetic pipelines, particularly in modeling temporal degradations, further hinder progress. Moreover, existing VIS methods are not robust to the degradations found in low-light videos and, consequently, perform poorly even after finetuning. In this paper, we introduce \textbf{ELVIS} (\textbf{E}nhance \textbf{L}ow-Light for \textbf{V}ideo \textbf{I}nstance \textbf{S}egmentation), a framework that enables domain adaptation of state-of-the-art VIS models to low-light scenarios. ELVIS is comprised of an unsupervised synthetic low-light video pipeline that models both spatial and temporal degradations, a calibration-free degradation profile estimation network (VDP-Net) and an enhancement decoder head that disentangles degradations from content features. ELVIS improves performances by up to \textbf{+3.7AP} on the synthetic low-light YouTube-VIS 2019 dataset and beats two-stage baselines by at least \textbf{+2.8AP} on real low-light videos. Code and dataset available at: \href{https://joannelin168.github.io/research/ELVIS}{https://joannelin168.github.io/research/ELVIS}

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑