Research map / 3D vision / 3D generation
SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis
Wenkun He, Yun Liu, Ruitao Liu, Li Yi
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 |
|---|---|---|---|
| add frequency decomposition (ablation) | SyncDiff · TACO Test1 | RA (%): 56.60 -> 73.28 | Improved |
| add alignment loss L_align (ablation) | SyncDiff · TACO Test1 | RA (%): 67.82 -> 73.28 | Improved |
| add explicit synchronization (ablation) | SyncDiff · TACO Test1 | RA (%): 67.27 -> 73.28 | Improved |
| add explicit synchronization (ablation) | SyncDiff · TACO Test1 | CSIoU (%): 65.51 -> 73.00 | Improved |
| add frequency decomposition (ablation) | SyncDiff · TACO Test1 | CSIoU (%): 68.86 -> 73.00 | Improved |
| add frequency decomposition (ablation) | SyncDiff · TACO Test4 | CSIoU (%): 28.07 -> 26.70 | Hurt |
| add frequency decomposition alone, without L_align and explicit sync (ablation) | SyncDiff · TACO Test1 | IV (cm3): 7.95 -> 14.28 | Hurt |
| add frequency decomposition (ablation) | SyncDiff · CORE4D Test1 | RA (%): 75.13 -> 92.89 | Improved |
| add explicit synchronization (ablation) | SyncDiff · CORE4D Test1 | RA (%): 80.20 -> 92.89 | Improved |
| add L_align (ablation) | SyncDiff · CORE4D Test1 | RA (%): 90.36 -> 92.89 | Improved |
| add all three components (ablation) | SyncDiff · OAKINK2 | RA (%): 48.96 -> 74.83 | Improved |
| add explicit synchronization (ablation) | SyncDiff · OAKINK2 | CSIoU (%): 58.05 -> 72.14 | Improved |
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.
- CG-HOI — CG-HOI: Contact-Guided 3D Human-Object Interaction Generation (CVPR 2024) · better on 2 of 2 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
- DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model (AAAI 2025 · similarity 0.89)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.89)
- InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions (CVPR 2025 · similarity 0.89)
- CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects (NeurIPS 2025 · similarity 0.88)
- SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios (NeurIPS 2025 · similarity 0.88)
- CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement (CVPR 2025 · similarity 0.88)
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.
