Research map / 3D vision / 3D generation
Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the proposed affordance model instead of the baseline | 3D affordance prediction with RGB input · SUNCG evaluation scenes | semantic score: 72.53 -> 91.69 | Helped |
| use the proposed affordance model instead of the baseline | 3D affordance prediction with RGB input · SUNCG evaluation scenes | geometry score: 23.25 -> 66.40 | Helped |
| add geometry-aware adversarial training (ablation) | proposed model with RGB input · SUNCG evaluation scenes | geometry score: 62.71 -> 66.40 | Helped |
| jointly train the where and what modules (ablation) | proposed model with RGB input · SUNCG evaluation scenes | semantic score: 83.34 -> 91.69 | Helped |
| add world-coordinate geometry loss (ablation) | proposed model with RGB input · SUNCG evaluation scenes | geometry score: 56.11 -> 66.40 | Helped |
| include scene depth information | proposed affordance model · SUNCG evaluation scenes | geometry score: 66.40 -> 71.17; 66.40 -> 72.11 | Helped |
| replace the separate where and what modules with a single VAE | RGB affordance prediction · SUNCG evaluation scenes | semantic score: 91.69 -> 76.23 | Hurt |
| replace the separate where and what modules with a single VAE | RGB affordance prediction · SUNCG evaluation scenes | geometry score: 66.40 -> 52.94 | Hurt |
Closest papers by meaning
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.89)
- Vision-Guided Action: Enhancing 3D Human Motion Prediction with Gaze-informed Affordance in 3D Scenes (CVPR 2025 · similarity 0.89)
- Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions (CVPR 2025 · similarity 0.89)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.88)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.88)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 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.