Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement Under Extreme Noise

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Ruirui, Huang, Guoxi, Anantrasirichai, Nantheera
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914589119086592
author Lin, Ruirui
Huang, Guoxi
Anantrasirichai, Nantheera
author_facet Lin, Ruirui
Huang, Guoxi
Anantrasirichai, Nantheera
contents Low-light video enhancement (LLVE) is challenging due to noise, low contrast, and color degradation. While learning-based methods enable fast inference, they often fail under heavy real-world noise because they do not sufficiently exploit long-term temporal cues. We propose DWTA-Net, a novel deep-learning recurrent LLVE framework with a recurrent design. DWTA-Net adopts an integrated two-stage architecture: Stage I restores local structure and color via multi-frame alignment for temporally consistent Mamba-based enhancement, while Stage II performs recurrent refinement using a novel dynamic weight-based temporal aggregation guided by optical flow, functioning as a recurrent denoiser that adapts to motion. We further introduce a texture-adaptive loss that preserves fine details in textured regions while suppressing noise in homogeneous areas. Experiments on real-world low-light footage show that DWTA-Net achieves stronger noise suppression and fewer artifacts, delivering superior visual quality compared with state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09450
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement Under Extreme Noise
Lin, Ruirui
Huang, Guoxi
Anantrasirichai, Nantheera
Computer Vision and Pattern Recognition
Low-light video enhancement (LLVE) is challenging due to noise, low contrast, and color degradation. While learning-based methods enable fast inference, they often fail under heavy real-world noise because they do not sufficiently exploit long-term temporal cues. We propose DWTA-Net, a novel deep-learning recurrent LLVE framework with a recurrent design. DWTA-Net adopts an integrated two-stage architecture: Stage I restores local structure and color via multi-frame alignment for temporally consistent Mamba-based enhancement, while Stage II performs recurrent refinement using a novel dynamic weight-based temporal aggregation guided by optical flow, functioning as a recurrent denoiser that adapts to motion. We further introduce a texture-adaptive loss that preserves fine details in textured regions while suppressing noise in homogeneous areas. Experiments on real-world low-light footage show that DWTA-Net achieves stronger noise suppression and fewer artifacts, delivering superior visual quality compared with state-of-the-art methods.
title Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement Under Extreme Noise
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.09450