Research map / Point clouds / Point cloud classification
AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers
Nghia Vu, Tuong Do, Khang Nguyen, Baoru Huang, Nhat Le, Binh Xuan Nguyen, Erman Tjiputra, Quang D. Tran, Ravi Prakash, Te-Chuan Chiu, Anh Nguyen
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 AffordMatcher cross-modal match-to-match attention instead of the best baseline | AffordMatcher · AffordBridge test | mAP: 45.6 -> 53.4 | Improved |
| use AffordMatcher instead of OpenMask3D-F | AffordMatcher · AffordBridge test | inference speed (ms/sample): 315.1 -> 112.5 | Improved |
| add the 2D RGB visual signifier branch (ablation) | AffordMatcher · AffordBridge test | mAP: 37.3 -> 53.4 | Improved |
| keep humans and hands visible in RGB signifiers (ablation) | AffordMatcher · AffordBridge test | mAP: 40.9 -> 53.4 | Improved |
| downsample point clouds to 100,000 points (ablation) | AffordMatcher · AffordBridge test | mAP: 48.7 -> 53.4 | Improved |
| train on AffordBridge scene data instead of fine-tuning on object-centric PIAD (ablation) | AffordMatcher · AffordBridge test | mAP: 45.3 -> 53.4 | Improved |
| add L_align to baseline objective (ablation) | AffordMatcher · AffordBridge test | mAP: 37.3 -> 40.9 | Improved |
| add L_dissim alongside L_align (ablation) | AffordMatcher · AffordBridge test | mAP: 40.9 -> 44.1 | Improved |
| add L_embed (ablation) | AffordMatcher · AffordBridge test | mAP: 44.1 -> 47.8 | Improved |
| add L_bidir for the full objective (ablation) | AffordMatcher · AffordBridge test | mAP: 47.8 -> 53.4 | Improved |
Closest papers by meaning
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.91)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.90)
- TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances (AAAI 2025 · similarity 0.90)
- 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds (ICLR 2025 · similarity 0.90)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.90)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.89)
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.
