Research map / Point clouds / Point cloud classification
QueryMe: Query-Driven Open-Vocabulary 3D Object Affordances Grounding from Multimodal Evidence
Weiyu Zhao, Ru Li, Jiaqi Liu, Sizhe Zhao, Qinglin Liu, Shengping Zhang
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 QueryMe instead of GREAT | 3D affordance grounding · PIADv2 Unseen Affordance | AUC: 69.81 -> 74.00 | Improved |
| use QueryMe instead of GREAT | 3D affordance grounding · PIADv2 Unseen Object | MAE: 0.109 -> 0.118 | Hurt |
| add multimodal evidence-guided queries (object, HOI, text) over concatenated features (ablation) | QueryMe · PIADv2 Unseen Affordance | AUC: 67.42 -> 74.00 | Improved |
| add text prompt features on top of object and 3D HOI features (ablation) | QueryMe · PIADv2 Unseen Affordance | AUC: 71.48 -> 74.00 | Improved |
| add text prompt features on top of object and 3D HOI features (ablation) | QueryMe · PIADv2 Unseen Object | aIoU: 23.15 -> 21.76 | Hurt |
| add cross-attention between text and HOI/object features (ablation) | QueryMe · PIADv2 Unseen Object | AUC: 76.69 -> 83.03 | Improved |
| add Adaptive Spatial Attention module (ablation) | QueryMe · PIADv2 Unseen Affordance | AUC: 67.85 -> 74.00 | Improved |
| use reconstructed 3D HOI features instead of 2D ResNet18 image features (ablation) | QueryMe · PIADv2 Unseen Affordance | AUC: 60.50 -> 74.00 | Improved |
| use 3D RoPE instead of MLP positional encoder for queries (ablation) | QueryMe · PIADv2 | performance | No clear effect |
| use QueryMe under point-cloud noise injection instead of GREAT | 3D affordance grounding · PIADv2 noise ratio 0.85 | AUC: about 63% -> about 69% | Improved |
Closest papers by meaning
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.93)
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.91)
- Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions (CVPR 2025 · similarity 0.91)
- 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds (ICLR 2025 · similarity 0.91)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.91)
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · 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.
