---
title: "Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition"
authors:
  - "Xiaogang Xu"
  - "Kun Zhou"
  - "Tao Hu"
  - "Jiafei Wu"
  - "Ruixing Wang"
  - "Hao Peng"
  - "Bei Yu"
doi: "10.24963/ijcai.2025/238"
url: "https://ijcai.org/proceedings/2025/238"
pdf: "https://ijcai.org/proceedings/2025/0238.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "2134-2142"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Computational photography"
  - "Computer Vision: CV: Low-level Vision"
---

# Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition

Xiaogang Xu, Kun Zhou, Tao Hu, Jiafei Wu, Ruixing Wang, Hao Peng, Bei Yu

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 2134-2142. DOI: [10.24963/ijcai.2025/238](https://doi.org/10.24963/ijcai.2025/238)

## Abstract

Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise. In this paper, we present an innovative video decomposition strategy that incorporates view-independent and view-dependent components to enhance the performance of LLVE. We leverage dynamic cross-frame correspondences for the view-independent term (which primarily captures intrinsic appearance) and impose a scene-level continuity constraint on the view-dependent term (which mainly describes the shading condition) to achieve consistent and satisfactory decomposition results. To further ensure consistent decomposition, we introduce a dual-structure enhancement network featuring a cross-frame interaction mechanism. By supervising different frames simultaneously, this network encourages them to exhibit matching decomposition features. This mechanism can seamlessly integrate with encoder-decoder single-frame networks, incurring minimal additional parameter costs. Extensive experiments are conducted on widely recognized LLVE benchmarks, covering diverse scenarios. Our framework consistently outperforms existing methods, establishing a new SOTA performance.