Research map / Vision-language and multimodal / Multimodal LLMs
UniRAP: Towards Unified Part-level Physical Affordance Reasoning and Actionable Perception
Linfei Li, Ruining Hu, Lin Zhang, Zhong Wang, Fengyi Zhang, Ying Shen, Binqiang Wang, Xin Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes UniRAP, a unified model that infers part-level physical affordances from visual observations and maps language instructions to actionable geometric representations.
Problem
Grounding high-level language semantics into part-level physical interaction (affordance reasoning) remains challenging for vision-language perception models.
Approach
A single unified model that performs part-level physical affordance reasoning and maps language instructions to actionable geometric representations, rather than separate perception and grounding stages.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add affordance pre-training stage (ablation) | UniRAP 3B · 3DOI referring | gIoU: 40.5 -> 50.4 | Improved |
| add affordance pre-training stage (ablation) | UniRAP 3B · 3DOI reasoning | gIoU: 37.5 -> 52.9 | Improved |
| add actionable affordance fine-tuning (ablation) | UniRAP 3B · RealVLG-Bench | grasp gAcc: 19.6 -> 63.3 | Improved |
| add visual referring pre-training (ablation) | UniRAP 3B · RealVLG-Bench | grasp gAcc: 26.4 -> 63.3 | Improved |
| use regression-based Grasp Head instead of heatmap head (ablation) | UniRAP 3B · RealVLG-Bench | grasp gAcc: 13.4 -> 63.3 | Improved |
| add Bbox Head (ablation) | UniRAP 3B · ReasonSeg | gIoU: 56.8 -> 57.9 | Improved |
| add Bbox Head (ablation) | UniRAP 3B · ReVOS | J&F: 60.4 -> 61.9 | Improved |
| add Bbox Head (ablation) | UniRAP 3B · RealVLG-Bench | grasp gAcc: 24.7 -> 63.3 | Improved |
| heatmap grasp head instead of UniRAP head (ablation) | UniRAP 3B · 3DOI referring | gIoU: 52.3 vs 52.1 | No clear effect |
| use UniRAP (3B) instead of RAGNet (7B) | affordance segmentation · 3DOI zero-shot reasoning | gIoU: +17.6 | Improved |
| end-to-end grasp head instead of text-generated grasp | UniRAP vs RealVLG-R1 · RealVLG-Bench Novel | grasp gAcc: 18.9 -> 63.3 | Improved |
| UniRAP 3B vs larger specialized VideoLISA on reasoning | UniRAP · ReasonSeg | cIoU: 67.1 (VideoLISA) vs 59.0 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HyperSeg — HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver (CVPR 2025) · better on 1 of 1 shared result
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
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.90)
- Probing and Bridging Geometry-Interaction Cues for Affordance Reasoning in Vision Foundation Models (CVPR 2026 · similarity 0.89)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.89)
- Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions (CVPR 2025 · similarity 0.89)
- UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation (NeurIPS 2026 · similarity 0.89)
- 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.
