Research map / 3D vision / Gaussian splatting
Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction
Hao Tian, Chenyangguang Zhang, Rui Liu, Wen Shen, Xiaolin Qin
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 interaction-aware module (w, o and training scheme) (ablation) | Interaction-aware 4D-GS · HOI4D ablation | PSNR: 28.76 -> 32.96 | Improved |
| add interaction-aware module (ablation) | Interaction-aware 4D-GS · HOI4D ablation | LPIPS: 0.40 -> 0.35 | Improved |
| add HOI refinement (ablation) | Interaction-aware 4D-GS · HOI4D ablation | PSNR: 32.23 -> 32.96 | Improved |
| add object loss (ablation) | Interaction-aware 4D-GS · HOI4D ablation | PSNR: 31.45 -> 32.96 | Improved |
| add hand loss (ablation) | Interaction-aware 4D-GS · HOI4D ablation | PSNR: 32.45 -> 32.96 | Improved |
| add interaction loss (ablation) | Interaction-aware 4D-GS · HOI4D ablation | PSNR: 31.79 -> 32.96 | Improved |
| add interaction loss (ablation) | Interaction-aware 4D-GS · HOI4D ablation | LPIPS: 0.40 -> 0.35 | Improved |
| add Gaussian noise (sigma 0.01) to initial object positions (ablation) | Interaction-aware 4D-GS · HOI4D ablation | PSNR: 32.96 -> 32.80 | No clear effect |
| add Gaussian noise (sigma 0.05) to initial object positions (ablation) | Interaction-aware 4D-GS · HOI4D ablation | PSNR: 32.96 -> 32.72 | No clear effect |
| evaluate on full frames instead of alternate frames | Interaction-aware 4D-GS · HOI4D translation scenes | PSNR: 30.32 -> 33.03 | Improved |
| evaluate hand and object regions only | Interaction-aware 4D-GS · HO3D translation-rotation | PSNR: 25.19 -> 28.16 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- SC-GS — SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (CVPR 2024) · better on 5 of 5 shared results
- BIGS — BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025) · better on 3 of 3 shared results
- HOLD — HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024) · better on 3 of 3 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
- Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars (NeurIPS 2024 · similarity 0.92)
- BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- Single-view Image to Novel-view Generation for Hand-Object Interactions (AAAI 2025 · similarity 0.90)
- HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data Augmentation (AAAI 2025 · similarity 0.89)
- Hand-Centric Motion Refinement for 3D Hand-Object Interaction via Hierarchical Spatial-Temporal Modeling (AAAI 2024 · similarity 0.88)
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.87)
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.
