Research map / Detection and segmentation / Open-set and few-shot detection
Exploiting Contextual Objects and Relations for 3D Visual Grounding
Li Yang, Chunfeng Yuan, Ziqi Zhang, Zhongang Qi, Yan Xu, Wei Liu, Ying Shan, Bing Li, Weiping Yang, Peng Li, Yan Wang, Weiming Hu
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 learning of contextual objects (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 34.66 -> 44.42 | Improved |
| add learning of contextual relations only (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 34.66 -> 37.33 | Improved |
| add both contextual objects and relations (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 34.66 -> 49.57 | Improved |
| add contextual relations on top of objects (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 44.42 -> 49.57 | Improved |
| supervised learning on labeled noun phrases (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 34.66 -> 38.33 | Improved |
| add pseudo labels for unlabeled noun phrases (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 38.33 -> 44.42 | Improved |
| add Distance & Orientation relation features (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 44.42 -> 46.57 | Improved |
| add Volume & Dimension relation features (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 44.42 -> 46.05 | Improved |
| add Perspective-related relation features (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 44.42 -> 47.44 | Improved |
| perspective features on view-dependent subset (ablation) | CORE-3DVG baseline · Nr3D View-dep. | Acc@0.25: 40.75 -> 46.46 | Improved |
| combine all three relation feature types (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 44.42 -> 47.90 | Improved |
| add relation matching network without weakly-supervised losses (ablation) | CORE-3DVG baseline · Nr3D overall | Acc@0.25: 47.90 -> 47.80 | No clear effect |
Closest papers by meaning
- AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring (AAAI 2025 · similarity 0.91)
- Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency (CVPR 2024 · similarity 0.91)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.90)
- Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners (CVPR 2024 · similarity 0.89)
- Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding (CVPR 2024 · similarity 0.89)
- Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding (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.
