Research map / 3D vision / 3D generation
Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement
Lian He, Meng Liu, Qilang Ye, Yu Zhou, Xiang Deng, Gangyi Ding
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 affordance-weighted frame selection (ablation) | TASA 2D detection · SceneFun3D Split0 | mIoU: 4.4 -> 11.3 | Improved |
| add double-check point validation (ablation) | TASA 2D detection · SceneFun3D Split0 | mAP: 3.9 -> 13.1 | Improved |
| use both frame selection and double check (ablation) | TASA 2D detection · SceneFun3D Split0 | mAP: 3.9 -> 23.2 | Improved |
| add color and text inputs to the 3D refinement module (ablation) | TASA 3D refinement · SceneFun3D Split0 | mAP: 23.2 -> lower (see Table 4) | Hurt |
| select K=10 frames instead of K=20 (ablation) | TASA frame selection · SceneFun3D | mIoU | No clear effect |
| use only one frame for selection (ablation) | TASA frame selection · SceneFun3D | mIoU | Hurt |
| replace Fun3DU's 2D lifting with TASA | Fun3DU · SceneFun3D | mAP: 7.6 -> 23.2 | Improved |
| replace Fun3DU with TASA | Fun3DU · SceneFun3D | AP25: 33.3 -> 28.6 | Hurt |
| replace Fun3DU with TASA | Fun3DU · SceneFun3D | inference time (s/sample): 130.26 -> 37.61 | Improved |
Closest papers by meaning
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.93)
- 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds (ICLR 2025 · similarity 0.92)
- UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation (NeurIPS 2026 · similarity 0.91)
- LASO: Language-guided Affordance Segmentation on 3D Object (CVPR 2024 · similarity 0.90)
- AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models (NeurIPS 2025 · similarity 0.90)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.90)
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.
