Research map / Vision-language and multimodal / Multimodal LLMs
Error-Driven Scene Editing for 3D Grounding in Large Language Models
Yue Zhang, Zun Wang, Han Lin, Jialu Li, Jianing Yang, Yonatan Bitton, Idan Szpektor, Mohit Bansal
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 Round 1 counterfactual scene editing | Chat-Scene (3D-only) · ScanRefer | Acc@0.25: 41.2 -> 45.5 | Improved |
| add Round 2 error-guided refinement after Round 1 (ablation) | Chat-Scene (3D-only) · ScanRefer | Acc@0.25: 45.5 -> 47.1 | Improved |
| add Round 1 counterfactual scene editing | Chat-Scene · ScanRefer | Acc@0.25: 55.5 -> 57.8 | Improved |
| add Round 2 error-guided refinement after Round 1 (ablation) | Chat-Scene · Multi3DRefer | F1@0.5: 55.8 -> 56.8 | Improved |
| add Round 3 iterative refinement (ablation) | DEER-3D · ScanRefer | Acc@0.5: 56.8 -> 56.7 | No clear effect |
| add edits on distractors, scale Edit-0 to Edit-3 (ablation) | DEER-3D · ScanRefer and Multi3DRefer | grounding accuracy | Improved |
| use targeted error-guided edits instead of random augmentation at equal data scale (ablation) | DEER-3D · ScanRefer | Acc@0.5: 50.9 -> 52.3 | Improved |
| add error-guided text-only augmentation instead of random text (ablation) | Chat-Scene · ScanRefer | Acc@0.25: 55.8 -> 56.4 | Improved |
| apply DEER-3D to Chat-Scene on ScanRefer Multiple subset | DEER-3D · ScanRefer Multiple | Acc@0.25: 47.8 -> 50.8 | Improved |
| apply DEER-3D to Chat-Scene on ScanRefer Unique subset | DEER-3D · ScanRefer Unique | Acc@0.25: 89.6 -> 88.6 | Hurt |
| apply DEER-3D to LL3DA backbone | DEER-3D · ScanRefer | Acc@0.25: 25.7 -> 29.2 | Improved |
| apply DEER-3D on Beacon3D | DEER-3D · Beacon3D | Overall (Obj): 41.0 -> 45.7 | Improved |
Closest papers by meaning
- 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)
- DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding (ICLR 2025 · similarity 0.89)
- AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring (AAAI 2025 · similarity 0.89)
- UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation (NeurIPS 2026 · similarity 0.89)
- G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 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.
