Research map / Point clouds / Point cloud classification
3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds
Lichen Zhao, Daigang Cai, Lu Sheng, Dong Xu
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 multiplex-attention cross-modal fusion to ScanRefer-like baseline (ablation) | 3DVG-Transformer · ScanRefer val (2D+3D) | Acc@0.5: 26.66 -> 31.15 | Improved |
| add multiplex-attention cross-modal fusion (ablation) | 3DVG-Transformer · ScanRefer val (2D+3D) | Acc@0.25: 41.45 -> 43.65 | Improved |
| add feature augmentation (proposal copy&paste, word erase) (ablation) | 3DVG-Transformer · ScanRefer val (2D+3D) | Acc@0.5: 31.15 -> 32.25 | Improved |
| add feature augmentation (ablation) | 3DVG-Transformer · ScanRefer val (2D+3D) | Acc@0.25: 43.65 -> 45.76 | Improved |
| add coordinate-guided contextual aggregation (CCA) (ablation) | 3DVG-Transformer · ScanRefer val (2D+3D) | Acc@0.5: 32.25 -> 34.67 | Improved |
| add coordinate-guided contextual aggregation (CCA) (ablation) | 3DVG-Transformer · ScanRefer val (2D+3D) | Acc@0.25: 45.76 -> 47.57 | Improved |
| add spatial proximity matrix to the attention matrix (Add-SPM) vs no SPM (ablation) | 3DVG-Transformer · Nr3D val | overall accuracy: 36.6% -> 40.8% | Improved |
| fuse SPM by addition instead of multiplication (ablation) | 3DVG-Transformer · Nr3D val | overall accuracy: 38.7% -> 40.8% | Improved |
| multiply SPM with attention versus no SPM (ablation) | 3DVG-Transformer · Nr3D val | overall accuracy: 36.6% -> 38.7% | Improved |
| add SPM (addition) on view-dependent subset (ablation) | 3DVG-Transformer · Nr3D val (view-dep) | accuracy: 32.6% -> 34.8% | Improved |
| Mul SPM vs Add SPM on view-dependent subset (ablation) | 3DVG-Transformer · Nr3D val (view-dep) | accuracy: 34.8% -> 34.8% | No clear effect |
| use full 3DVG-Transformer instead of ScanRefer baseline (multiple-object subset, 2D+3D) | 3DVG-Transformer · ScanRefer val (multiple) | Acc@0.25: 32.73 -> 39.30 | Improved |
Later papers that compared with this method
2 later accepted papers report 3DVG-Transformer as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds (CVPR 2022 · better on 6 of 6 shared results)
- 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection (CVPR 2022 · better on 2 of 2 shared results)
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 3 of 4 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
- AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring (AAAI 2025 · similarity 0.91)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.90)
- SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding (NeurIPS 2025 · similarity 0.90)
- G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding (CVPR 2024 · similarity 0.90)
- LIBA: Language Instructed Multi-granularity Bridge Assistant for 3D Visual Grounding (AAAI 2025 · similarity 0.90)
- Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency (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.
