Research
ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark
arXiv:2512.01495v3 Announce Type: replace Abstract: Video instance segmentation (VIS) for low-light content remains highly challenging for both humans and machines alike, due to noise, blur and other
arXiv:2512.01495v3 Announce Type: replace Abstract: 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 extbf{ELVIS} (extbf{E}nhance extbf{L}ow-Light for extbf{V}ideo extbf{I}nstance extbf{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 extbf{+3.7AP} on the synthetic low-light YouTube-VIS 2019 dataset and beats two-stage baselines by at least extbf{+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}
Related
- RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
- TDiR: Transformer based Diffusion for Image Restoration Tasks
- Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark
- SA-VIS: Sparse frame Annotations for training Video Instance Segmentation
Source: arXiv cs.CV | 2026-10-14