Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition

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

doi:10.24963/ijcai.2025/238

Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition

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

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 2134-2142.

https://doi.org/10.24963/ijcai.2025/238

Keywords

Computer Vision: CV: Computational photography
Computer Vision: CV: Low-level Vision

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.

Xiaogang Xu, Kun Zhou, Tao Hu, Jiafei Wu, Ruixing Wang, Hao Peng, and Bei Yu. 2025. Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 2134–2142. https://doi.org/10.24963/ijcai.2025/238

@inproceedings{ijcai2025p238,
  title     = {Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition},
  author    = {Xu, Xiaogang and Zhou, Kun and Hu, Tao and Wu, Jiafei and Wang, Ruixing and Peng, Hao and Yu, Bei},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {2134--2142},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/238},
  url       = {https://doi.org/10.24963/ijcai.2025/238},
}

TY  - CPAPER
TI  - Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition
AU  - Xu, Xiaogang
AU  - Zhou, Kun
AU  - Hu, Tao
AU  - Wu, Jiafei
AU  - Wang, Ruixing
AU  - Peng, Hao
AU  - Yu, Bei
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 2134
EP  - 2142
DO  - 10.24963/ijcai.2025/238
UR  - https://doi.org/10.24963/ijcai.2025/238
ER  -