Research map / 3D vision / 3D generation
SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild
Patrick Rim, Kevin Harris, Braden Copple, Shangchen Han, Xu Xie, Ivan Shugurov, Sizhe An, He Wen, Alex Wong, Tomas Hodan, Kun He
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 SHOW3D instead of studio HOT3D, test on the other dataset | InterField · Interaction field (cross-dataset) | ADE (mm): 22.57 -> 14.70 | Improved |
| add SHOW3D to HOT3D training | InterField · Interaction field, test on HOT3D | ADE (mm): 11.29 -> 8.80 | Improved |
| add HOT3D to SHOW3D training | InterField · Interaction field, test on SHOW3D | ADE (mm): 13.82 -> 13.50 | No clear effect |
| train on SHOW3D instead of UmeTrack | UmeTrack hand model · 3D hand pose, test on SHOW3D | MKPE (mm): 22.2 -> 15.5 | Improved |
| add SHOW3D to UmeTrack + HOT3D training | UmeTrack hand model · 3D hand pose, test on SHOW3D | MKPE (mm): 16.4 -> 14.3 | Improved |
| add SHOW3D to UmeTrack + HOT3D training | UmeTrack hand model · 3D hand pose, test on UmeTrack | MKPE (mm): 9.5 -> 9.6 | No clear effect |
| add text caption conditioning | forecasting transformer · Object pose forecasting, 30 frames ahead | mean translation error (mm): 42.7 -> 30.4 | Improved |
| add text caption conditioning | forecasting transformer · Object pose forecasting, 60 frames ahead | mean translation error (mm): 46.7 -> 35.0 | Improved |
| add text conditioning on some objects | forecasting transformer · Object pose forecasting, 30 frames ahead (aria) | translation error (mm): 58.5 -> 49.0 | Improved |
Closest papers by meaning
- HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos (CVPR 2025 · similarity 0.92)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (CVPR 2025 · similarity 0.89)
- HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction (NeurIPS 2025 · similarity 0.89)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.89)
- MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation (NeurIPS 2025 · similarity 0.89)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · 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.
