Coming Out of the Dark: Human Pose Estimation in Low-light Conditions

Su, Yong; Chen, Defang; Xing, Meng; Oh, Changjae; Liu, Xuewei; Li, Jieyang

doi:10.24963/ijcai.2025/210

Coming Out of the Dark: Human Pose Estimation in Low-light Conditions

Yong Su, Defang Chen, Meng Xing, Changjae Oh, Xuewei Liu, Jieyang Li

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1882-1890.

https://doi.org/10.24963/ijcai.2025/210

Keywords

Computer Vision: CV: Machine learning for vision
Humans and AI: HAI: Human-computer interaction
Computer Vision: CV: Applications and Systems
Computer Vision: CV: Interpretability and transparency

Abstract

Human pose estimation in low-light conditions is vital for applications such as surveillance and autonomous systems, yet the severe visual distortions hinder both manual annotation and estimation precision. Existing approaches typically rely on additional reference information to mitigate these issues, however, customized data collection equipment poses limitations on their scalability. To alleviate the issue, we construct a Low-Light Images and Poses (LLIP) dataset, which includes only paired low-light images and pose annotations obtained using off-the-shelf motion capture devices. Furthermore, we propose a Multi-grained High-frequency Feature Consistency Learning framework (MHFCL), which does not rely on additional reference information. MHFCL employs a Retinex-inspired restoration stream to recover high-frequency details and integrates them into pose estimation using a multi-grained consistency mechanism. Experiments demonstrate that our approach achieves a new benchmark in low-light pose estimation, while maintaining competitive performance in well-lit conditions.

Yong Su, Defang Chen, Meng Xing, Changjae Oh, Xuewei Liu, and Jieyang Li. 2025. Coming Out of the Dark: Human Pose Estimation in Low-light Conditions. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 1882–1890. https://doi.org/10.24963/ijcai.2025/210

@inproceedings{ijcai2025p210,
  title     = {Coming Out of the Dark: Human Pose Estimation in Low-light Conditions},
  author    = {Su, Yong and Chen, Defang and Xing, Meng and Oh, Changjae and Liu, Xuewei and Li, Jieyang},
  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     = {1882--1890},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/210},
  url       = {https://doi.org/10.24963/ijcai.2025/210},
}

TY  - CPAPER
TI  - Coming Out of the Dark: Human Pose Estimation in Low-light Conditions
AU  - Su, Yong
AU  - Chen, Defang
AU  - Xing, Meng
AU  - Oh, Changjae
AU  - Liu, Xuewei
AU  - Li, Jieyang
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  - 1882
EP  - 1890
DO  - 10.24963/ijcai.2025/210
UR  - https://doi.org/10.24963/ijcai.2025/210
ER  -