Research map / 3D vision / 3D generation
BEHAVE: Dataset and Method for Tracking Human Object Interactions
Bharat Lal Bhatnagar, Xianghui Xie, Ilya A. Petrov, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll
Check 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 |
|---|---|---|---|
| Use joint tracking with learned human/object correspondences, unsigned distance fields, and contact prediction instead of fitting models directly to point clouds | BEHAVE · BEHAVE | SMPL v2v (cm): 16.15 -> 4.99 | Improved |
| Use joint tracking with learned human/object correspondences, unsigned distance fields, and contact prediction instead of fitting models directly to point clouds | BEHAVE · BEHAVE | obj. v2v (cm): 26.09 -> 21.20 | Improved |
| Use BEHAVE instead of PHOSA | Human-object fitting · BEHAVE | SMPL v2v (cm): 13.73 -> 4.99 | Improved |
| Use BEHAVE instead of PHOSA | Human-object fitting · BEHAVE | obj. v2v (cm): 34.73 -> 21.20 | Improved |
| Use BEHAVE instead of IP-Net for human registration | Human registration · BEHAVE | SMPL v2v (cm): 6.61 -> 4.99 | Improved |
| Use BEHAVE instead of LoopReg for human registration | Human registration · BEHAVE | SMPL v2v (cm): 9.12 -> 4.99 | Improved |
| Add object orientation prediction (ablation) | BEHAVE · BEHAVE | obj. v2v (cm): 24.02 -> 21.20 | Improved |
| Add object orientation prediction (ablation) | BEHAVE · BEHAVE | SMPL v2v (cm): 4.98 -> 4.99 | No clear effect |
| Add contact prediction (ablation) | BEHAVE · BEHAVE | SMPL v2v (cm): 4.96 -> 4.99 | No clear effect |
| Add contact prediction (ablation) | BEHAVE · BEHAVE | obj. v2v (cm): 21.28 -> 21.20 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports BEHAVE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- HUMOTO: A 4D Dataset of Mocap Human Object Interactions (ICCV 2025 · better on 5 of 5 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- LoopReg — LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration (NeurIPS 2020) · better on 1 of 1 shared result
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
- HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment (CVPR 2024 · similarity 0.89)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.88)
- Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions (NeurIPS 2024 · similarity 0.88)
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.87)
- CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement (CVPR 2025 · similarity 0.86)
- Scaling Up Dynamic Human-Scene Interaction Modeling (CVPR 2024 · similarity 0.86)
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.
