Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yini, Anantrasirichai, Nantheera
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910091760893952
author Li, Yini
Anantrasirichai, Nantheera
author_facet Li, Yini
Anantrasirichai, Nantheera
contents Low-light and underwater videos suffer from poor visibility, low contrast, and high noise, necessitating enhancements in visual quality. However, existing approaches typically rely on paired ground truth, which limits their practicality and often fails to maintain temporal consistency. To overcome these obstacles, this paper introduces a novel zero-shot learning approach named Zero-TIG, leveraging the Retinex theory and optical flow techniques. The proposed network consists of an enhancement module and a temporal feedback module. The enhancement module comprises three subnetworks: low-light image denoising, illumination estimation, and reflection denoising. The temporal enhancement module ensures temporal consistency by incorporating histogram equalization, optical flow computation, and image warping to align the enhanced previous frame with the current frame, thereby maintaining continuity. Additionally, we address color distortion in underwater data by adaptively balancing RGB channels. The experimental results demonstrate that our method achieves low-light video enhancement without the need for paired training data, making it a promising and applicable method for real-world scenario enhancement.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11175
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement
Li, Yini
Anantrasirichai, Nantheera
Computer Vision and Pattern Recognition
Artificial Intelligence
Low-light and underwater videos suffer from poor visibility, low contrast, and high noise, necessitating enhancements in visual quality. However, existing approaches typically rely on paired ground truth, which limits their practicality and often fails to maintain temporal consistency. To overcome these obstacles, this paper introduces a novel zero-shot learning approach named Zero-TIG, leveraging the Retinex theory and optical flow techniques. The proposed network consists of an enhancement module and a temporal feedback module. The enhancement module comprises three subnetworks: low-light image denoising, illumination estimation, and reflection denoising. The temporal enhancement module ensures temporal consistency by incorporating histogram equalization, optical flow computation, and image warping to align the enhanced previous frame with the current frame, thereby maintaining continuity. Additionally, we address color distortion in underwater data by adaptively balancing RGB channels. The experimental results demonstrate that our method achieves low-light video enhancement without the need for paired training data, making it a promising and applicable method for real-world scenario enhancement.
title Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.11175