Research map / 3D vision / 3D generation
ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos
Yuantao Chen, Jiahao Chang, Chongjie Ye, Chaoran Zhang, Zhaojie Fang, Chenghong Li, Xiaoguang Han
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 |
|---|---|---|---|
| train on the synthetic HOI dataset instead of multi-view object data with random masks (ablation) | ForeHOI backbone · HO3D | Chamfer distance (cm): 1.23 -> 0.91 | Improved |
| train on the synthetic HOI dataset instead of multi-view object data with random masks (ablation) | ForeHOI backbone · HO3D | F-score@5mm (%): 25.54 -> 53.64 | Improved |
| add hand feature input (ablation) | ForeHOI · HO3D | Chamfer distance (cm): 0.91 -> 0.88 | Improved |
| add hand feature input (ablation) | ForeHOI · HO3D | F-score@10mm (%): 80.63 -> 85.43 | Improved |
| add 2D mask completion branch (ablation) | ForeHOI · HO3D | F-score@5mm (%): 54.53 -> 68.95 | Improved |
| add 2D mask completion branch (ablation) | ForeHOI · HO3D | Chamfer distance (cm): 0.88 -> 0.79 | Improved |
| compare feed-forward ForeHOI against MagicHOI | ForeHOI · HO3D | Chamfer distance (cm): 0.86 -> 0.79 | Improved |
| compare feed-forward ForeHOI against HOLD | ForeHOI · HO3D | F-score@5mm (%): 66.42 -> 68.95 | Improved |
| compare ForeHOI against HORT on HOT3D | ForeHOI · HOT3D | F-score@5mm (%): 16.52 -> 60.5 | Improved |
| compare ForeHOI pose against Dynhor | ForeHOI · HO3D object pose | RPE translation (cm): 4.25 -> 1.42 | Improved |
| compare ForeHOI inference time against HORT | ForeHOI · HO3D/HOT3D | average time (min): 0.8 -> 1.1 | Hurt |
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.
- HOLD — HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024) · better on 7 of 7 shared results
- MagicHOI — MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips (ICCV 2025) · 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
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (CVPR 2025 · similarity 0.92)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.90)
- HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions (CVPR 2024 · similarity 0.89)
- Hand-held Object Reconstruction from RGB Video with Dynamic Interaction (CVPR 2025 · similarity 0.89)
- BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- In-Hand 3D Object Reconstruction from a Monocular RGB Video (AAAI 2024 · similarity 0.89)
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.
