Research map / 3D vision / 3D generation
Understanding 3D Object Interaction from a Single Image
Shengyi Qian, David F. Fouhey
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 |
|---|---|---|---|
| use transformer with mask decoder instead of ResNet MLP / COHESIV query-point architectures | 3D object interaction model · 3DOI dataset | Box IoU: 28.3 -> 69.9 vs COHESIV | Improved |
| train on real image dataset with annotations rather than synthetic SAPIEN renderings | 3DADN · 3DOI dataset | Box IoU: 5.94 -> 8.53 (3DADN vs SAPIEN) | Improved |
| train on 3DOI dataset instead of human-interaction video data | articulated object detection · 3DOI dataset | Articulation type accuracy: 44.3 -> 89.4 | Improved |
| predict affordance from 3DOI-trained model instead of InteractionHotspots | affordance · 3DOI dataset | Affordance SIM: 0.047 -> 0.167 | Improved |
| zero-shot transfer to robotics data without finetuning | 3DOI-trained model · WHIRL | Box IoU: 37.1 -> 68.7 vs COHESIV | Improved |
| use dedicated mask decoder for dense predictions | 3D object interaction model · WHIRL | dense predictions (localization, affordance) | Improved |
| use COHESIV instead of ResNet MLP on movable prediction | baseline architectures · 3DOI dataset | Movable accuracy: 72.5 -> 71.5 | Hurt |
Closest papers by meaning
- Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description (ICCV 2025 · similarity 0.88)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.88)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.86)
- Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model (ICLR 2025 · similarity 0.86)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.86)
- RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics (CVPR 2025 · 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.
