Research map / Vision-language and multimodal / Human and embodied modeling
EG-3DVG: Expression and Geometry Aware Grounding Decoder for 3D Visual Grounding
GwangWook Park, Hyo-Jun Lee, Jong-Hyeon Baek, Hanul Kim, Yeong Jun Koh
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 PECA, GMA and ECL together (ablation) | EG-3DVG baseline decoder · ScanRefer | 3DREC Acc@0.5: 49.62 -> 52.36 | Improved |
| add PECA alone (ablation) | baseline decoder · ScanRefer | 3DRES mIoU: 44.19 -> 45.69 | Improved |
| add GMA alone (ablation) | baseline decoder · ScanRefer | 3DRES mIoU: 44.19 -> 46.19 | Improved |
| add ECL alone (ablation) | baseline decoder · ScanRefer | 3DRES mIoU: 44.19 -> 45.84 | Improved |
| add GMA alone (ablation) | baseline decoder · ScanRefer | 3DREC Acc@0.25: 57.04 -> 57.05 | No clear effect |
| add ECL on top of PECA and GMA (ablation) | EG-3DVG · ScanRefer | 3DRES mIoU: 46.57 -> 47.28 | Improved |
| add GMA on top of PECA and ECL (ablation) | EG-3DVG · ScanRefer | 3DREC Acc@0.5: 51.64 -> 52.36 | Improved |
| use text-and-geometry attention mask instead of fixed-radius mask in GMA (ablation) | GMA · ScanRefer | 3DREC Acc@0.5: 51.12 -> 52.36 | Improved |
| include text tokens in the GMA attention mask instead of geometric feature only (ablation) | GMA · ScanRefer | 3DRES mIoU: 46.70 -> 47.28 | Improved |
| EG-3DVG vs previous best single-stage TSP3D | TSP3D · ScanRefer single-stage | Acc@0.5: +3.36 | Improved |
| EG-3DVG vs MCLN in two-stage setting | MCLN · ScanRefer two-stage | Acc@0.5: +6.83 | Improved |
| EG-3DVG vs G3-LQ on SR3D hard subset | G3-LQ · SR3D hard | Acc@0.25: 66.3 -> 66.6 | No clear effect |
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.
- G3-LQ — G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding (CVPR 2024) · better on 4 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
- Mono3DVG: 3D Visual Grounding in Monocular Images (AAAI 2024 · similarity 0.91)
- G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding (CVPR 2024 · similarity 0.90)
- SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding (CVPR 2025 · similarity 0.90)
- AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring (AAAI 2025 · similarity 0.90)
- Grounded 3D-Aware Spatial Vision-Language Modeling (CVPR 2026 · similarity 0.90)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · 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.
