Research map / Vision-language and multimodal / Human and embodied modeling
VGMamba: Attribute-to-Location Clue Reasoning for Quantity-Agnostic 3D Visual Grounding
Yihang Zhu, Jinhao Zhang, Yuxuan Wang, Aming Wu, Cheng Deng
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 SVD-based Attribute Mamba (SAM) (ablation) | baseline · Multi3DRefer val | F1@0.5 All: 38.4 -> 45.2 | Improved |
| add SVD-based Attribute Mamba (SAM) (ablation) | baseline · Multi3DRefer val | F1@0.5 ST w/o D: 47.8 -> 67.6 | Improved |
| add Location Mamba (LM) (ablation) | baseline + SAM · Multi3DRefer val | F1@0.5 All: 45.2 -> 52.5 | Improved |
| add Location Mamba (LM) (ablation) | baseline + SAM · Multi3DRefer val | F1@0.5 MT: 47.8 -> 53.1 | Improved |
| add Instructive Dual-Mamba (IDM) (ablation) | SAM + LM · Multi3DRefer val | F1@0.5 All: 52.5 -> 54.9 | Improved |
| add Instructive Dual-Mamba (IDM) (ablation) | SAM + LM · Multi3DRefer val | F1@0.5 ZT w/D: 45.3 -> 45.2 | No clear effect |
| reason attribute first then location instead of location first (ablation) | VGMamba · Multi3DRefer val | F1@0.5 All: 53.1 -> 54.9 | Improved |
| VGMamba vs previous best PQ3D | VGMamba · ScanRefer val | Acc@0.5 overall: 51.2 -> 53.9 | Improved |
| VGMamba vs second best D-LISA | VGMamba · Multi3DRefer val | F1@0.5 MT: 51.0 -> 55.1 | Improved |
Later papers that compared with this method
1 later accepted paper reports VGMamba as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding (ECCV 2026 · better on 1 of 3 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
- 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 0.89)
- Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention (NeurIPS 2024 · similarity 0.89)
- ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning (CVPR 2025 · similarity 0.88)
- Reasoning in Space via Grounding in the World (ICLR 2026 · similarity 0.88)
- S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance (CVPR 2026 · 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.
