Research map / Vision-language and multimodal / Multimodal LLMs
Panoramic Affordance Prediction
Zixin Zhang, Chenfei Liao, Hongfei Zhang, Harold Haodong Chen, Kanghao Chen, Zichen Wen, Litao Guo, Bin Ren, Xu Zheng, Yinchuan Li, Xuming Hu, Nicu Sebe and 1 more
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 |
|---|---|---|---|
| add Visual Grid Prompting (without CoT) (ablation) | PAP · PAP-12K (10% subset) | gIoU: 57.70 -> 69.56 | Improved |
| add chain-of-thought prompting (without VGP) (ablation) | PAP · PAP-12K (10% subset) | gIoU: 57.70 -> 67.22 | Improved |
| add chain-of-thought on top of grid prompting (ablation) | PAP · PAP-12K (10% subset) | gIoU: 69.56 -> 72.69 | Improved |
| add Recursive Visual Routing (ablation) | PAP · PAP-12K (10% subset) | cIoU: 57.05 -> 63.85 | Improved |
| add Recursive Visual Routing on the Hard subset (ablation) | PAP · PAP-12K Hard (10% subset) | cIoU: 34.81 -> 47.11 | Improved |
| add Recursive Visual Routing on the Normal subset (ablation) | PAP · PAP-12K Normal (10% subset) | gIoU: 76.29 -> 77.07 | Improved |
| add Adaptive Gaze (ablation) | PAP · PAP-12K (10% subset) | gIoU: 64.99 -> 72.69 | Improved |
| use 4x3 grid instead of 2x2 (ablation) | PAP · PAP-12K (10% subset) | gIoU: 61.45 -> 72.69 | Improved |
| use 10x10 grid instead of 4x3 (ablation) | PAP · PAP-12K (10% subset) | gIoU: 72.69 -> 60.07 | Hurt |
| replace line grid with semi-transparent color blocks (ablation) | PAP · PAP-12K (10% subset) | gIoU: 70.91 to 68.67 | Hurt |
| increase grid line width to 50 pixels (ablation) | PAP · PAP-12K (10% subset) | gIoU: 72.69 -> 67.49 | Hurt |
| increase grid font size to 200 (ablation) | PAP · PAP-12K (10% subset) | cIoU: 63.85 -> 58.44 | 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.
- Affordance-R1 — Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Models (AAAI 2026) · better on 2 of 2 shared results
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
- Weakly Supervised Multimodal Affordance Grounding for Egocentric Images (AAAI 2024 · similarity 0.86)
- Vision-Guided Action: Enhancing 3D Human Motion Prediction with Gaze-informed Affordance in 3D Scenes (CVPR 2025 · similarity 0.86)
- Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions (CVPR 2025 · similarity 0.86)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.86)
- 360+x: A Panoptic Multi-modal Scene Understanding Dataset (CVPR 2024 · similarity 0.86)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.85)
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.
