{"type":"ScholarlyArticle","title":"Coming Out of the Dark: Human Pose Estimation in Low-light Conditions","authors":[{"name":"Yong Su","slug":"yong-su","given":"Yong","family":"Su","affiliation":""},{"name":"Defang Chen","slug":"defang-chen","given":"Defang","family":"Chen","affiliation":""},{"name":"Meng Xing","slug":"meng-xing","given":"Meng","family":"Xing","affiliation":""},{"name":"Changjae Oh","slug":"changjae-oh","given":"Changjae","family":"Oh","affiliation":""},{"name":"Xuewei Liu","slug":"xuewei-liu","given":"Xuewei","family":"Liu","affiliation":""},{"name":"Jieyang Li","slug":"jieyang-li","given":"Jieyang","family":"Li","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/210","url":"https://ijcai.org/proceedings/2025/210","pdf":"https://ijcai.org/proceedings/2025/0210.pdf","markdown":"https://ijcai.org/proceedings/2025/210.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/210","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":210,"pages":{"first":1882,"last":1890},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}