{"ID":2880112,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.14431","arxiv_id":"2508.14431","title":"HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation","abstract":"Monocular 3D human pose estimation (HPE) often encounters challenges such as depth ambiguity and occlusion during the 2D-to-3D lifting process. Additionally, traditional methods may overlook multi-scale skeleton features when utilizing skeleton structure information, which can negatively impact the accuracy of pose estimation. To address these challenges, this paper introduces a novel 3D pose estimation method, HyperDiff, which integrates diffusion models with HyperGCN. The diffusion model effectively captures data uncertainty, alleviating depth ambiguity and occlusion. Meanwhile, HyperGCN, serving as a denoiser, employs multi-granularity structures to accurately model high-order correlations between joints. This improves the model's denoising capability especially for complex poses. Experimental results demonstrate that HyperDiff achieves state-of-the-art performance on the Human3.6M and MPI-INF-3DHP datasets and can flexibly adapt to varying computational resources to balance performance and efficiency.","short_abstract":"Monocular 3D human pose estimation (HPE) often encounters challenges such as depth ambiguity and occlusion during the 2D-to-3D lifting process. Additionally, traditional methods may overlook multi-scale skeleton features when utilizing skeleton structure information, which can negatively impact the accuracy of pose est...","url_abs":"https://arxiv.org/abs/2508.14431","url_pdf":"https://arxiv.org/pdf/2508.14431v1","authors":"[\"Bing Han\",\"Yuhua Huang\",\"Pan Gao\"]","published":"2025-08-20T05:03:55Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}