Research map / 3D vision / Gaussian splatting
HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos
Lixin Xue, Chen Guo, Chengwei Zheng, Fangjinhua Wang, Tianjian Jiang, Hsuan-I Ho, Manuel Kaufmann, Jie Song, Otmar Hilliges
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| jointly optimize human and scene in a global coordinate system instead of human-centric reconstruction | Vid2Avatar · SHSD | Mask IoU: 0.923 -> 0.954 | Improved |
| holistic HSR instead of Vid2Avatar for human geometry | Vid2Avatar · SHSD | Chamfer distance (cm): 2.626 -> 2.349 | Improved |
| holistic HSR instead of PPR for scene reconstruction | PPR · SHSD subset | depth L1 error (cm): 42.29 -> 15.14 | Improved |
| joint global optimization instead of training human and scene separately (ablation) | HSR · real and SHSD videos | spatial alignment and segmentation | Improved |
| add shape-aware sampling restricted to the SMPL bounding box (ablation) | HSR · occlusion scenes | human shape consistency | Improved |
| enable pose condition late and periodically reset pose parameters to zero (ablation) | HSR · occlusion scenes | temporal shape consistency | Improved |
| add monocular depth and normal priors from Omnidata (ablation) | HSR · texture-less scene regions | scene reconstruction quality | Improved |
| add interpenetration loss (ablation) | HSR · contact regions | human-scene interpenetration | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Vid2Avatar — Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition (CVPR 2023) · better on 6 of 6 shared results
- SelfRecon — SelfRecon: Self Reconstruction Your Digital Avatar From Monocular Video (CVPR 2022) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.93)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.92)
- UniCon3R: Unified Contact-aware 4D Human-Scene Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.91)
- Synergistic Global-space Camera and Human Reconstruction from Videos (CVPR 2024 · similarity 0.90)
- Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses (CVPR 2024 · similarity 0.90)
- Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video (CVPR 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
