Research map / Point clouds / Point cloud classification
Free-Form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud
Mingtao Feng, Zhen Li, Qi Li, Liang Zhang, XiangDong Zhang, Guangming Zhu, Hui Zhang, Yaonan Wang, Ajmal Mian
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 the language scene graph module (ablation) | Ours · ScanRefer val | Acc@0.5 overall: 32.87 -> 34.01 | Improved |
| add the multi-level proposal relation graph module (ablation) | Ours · ScanRefer val | Acc@0.5 overall: 33.14 -> 34.01 | Improved |
| add the description guided 3D visual graph module (ablation) | Ours · ScanRefer val | Acc@0.5 overall: 31.90 -> 34.01 | Improved |
| add rgb to xyz input (ablation) | Ours · ScanRefer val | Acc@0.5 overall: 32.47 -> 33.55 | Improved |
| add normals to xyz+rgb input (ablation) | Ours · ScanRefer val | Acc@0.5 overall: 33.55 -> 34.01 | Improved |
| use ground truth boxes instead of VoteNet proposals (ablation) | Ours · ScanRefer val | Acc@0.5 overall: 34.01 -> 43.16 | Improved |
| use random same-class VoteNet proposal instead of the full model (ablation) | VoteNet · ScanRefer val | Acc@0.5 overall: 34.01 -> 5.28 | Hurt |
| ground in 2D images and project to 3D instead of directly in 3D (ablation) | One-stage · ScanRefer val | Acc@0.5 overall: 34.01 -> 9.04 | 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.
- InstanceRefer — InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds Through Instance Multi-Level Contextual Referring (ICCV 2021) · better on 7 of 7 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
- Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships (CVPR 2024 · similarity 0.90)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.89)
- Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention (NeurIPS 2024 · similarity 0.89)
- CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding (ICLR 2024 · similarity 0.88)
- Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding (CVPR 2024 · similarity 0.88)
- AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring (AAAI 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.
