Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Learning Affordance Landscapes for Interaction Exploration in 3D Environments
Tushar Nagarajan, Kristen Grauman
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 exploration to seek novel successful object interactions and learn visual affordance maps online | IntExp · AI2-iTHOR unseen test environments | average coverage: 16.77 -> 22.15 | Improved |
| train exploration to seek novel successful object interactions and learn visual affordance maps online | IntExp · AI2-iTHOR unseen test environments | average precision: 4.15 -> 8.46 | Improved |
| pretrain with interaction exploration before fine-tuning | downstream interaction policies · Retrieve and Store | success rate (%): 18.50 -> 27.25; 10.75 -> 27.00 | Improved |
| pretrain with interaction exploration before fine-tuning | downstream interaction policies · Wash and Heat | success rate (%): 1.50 -> 3.75; 2.25 -> 19.00 | Improved |
| use learned affordance maps instead of saliency-only maps (ablation) | IntExp affordance model · AI2-iTHOR unseen test environments | mAP: 13.4 -> 16.3 | Improved |
| mark the whole target object rather than a fixed-size point (ablation) | IntExp affordance model · AI2-iTHOR unseen test environments | mAP: 16.3 -> 26.5 | Improved |
| use ground-truth affordances instead of affordances learned online (ablation) | IntExp affordance model · AI2-iTHOR unseen test environments | mAP: 26.5 -> 37.3 | Improved |
| add an explicit learned affordance map rather than use RGB alone (ablation) | IntExp exploration policy · AI2-iTHOR unseen test environments | interaction exploration | Improved |
| use the hard count-based reward for each newly discovered interaction instead of softer repeated-interaction reward (ablation) | IntExp exploration policy · AI2-iTHOR unseen test environments | interaction coverage | Improved |
| use the hard count-based reward for each newly discovered interaction instead of rewarding unique actions regardless of object (ablation) | IntExp exploration policy · AI2-iTHOR unseen test environments | interaction coverage | Improved |
| interleave affordance training more frequently (ablation) | IntExp training schedule · AI2-iTHOR unseen test environments | mAP: +1.8% | Improved |
| interleave affordance training more frequently (ablation) | IntExp training schedule · AI2-iTHOR unseen test environments | interaction exploration | No clear effect |
Closest papers by meaning
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.90)
- An Interactive Navigation Method with Effect-oriented Affordance (CVPR 2024 · similarity 0.89)
- Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Models (CVPR 2026 · similarity 0.89)
- Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Models (AAAI 2026 · similarity 0.89)
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance (CVPR 2025 · similarity 0.88)
- AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models (NeurIPS 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.
