Research map / Point clouds / Point cloud classification
Ground3D-LMM: Fine-Grained 3D Point Grounding and Spatial Reasoning with LMM
Amol Harsh, Zongyan Han, Jean Lahoud, Ye Liu, Rao M Anwer, Hisham Cholakkal, Salman Khan, Fahad Shahbaz Khan
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 RGB image to point cloud input | Ground3D-LMM · Ground3D-ScanNet object seg | mIoU: 37.40 -> 42.22 | Improved |
| Add RGB image to point cloud input | Ground3D-LMM · Ground3D-ScanNet++ object seg | mIoU: 24.56 -> 30.42 | Improved |
| Add RGB image to point cloud input | Ground3D-LMM · Ground3D ScanNet++ text/metric | Mean APE: 84.15 -> 88.20 | Hurt |
| Train with 25% instead of full data (ablation) | Ground3D-LMM · Ground3D-ScanNet object | mIoU: 36.93 -> 42.22 | Improved |
| Add mask supervision to text-only supervision (ablation) | Ground3D-LMM · Ground3D-ScanNet object | APE: 77.41 -> 76.07 | No clear effect |
| Add clean masks versus 50% zeroed masks (ablation) | Ground3D-LMM · Ground3D-ScanNet object | mIoU: 41.06 -> 42.22 | Improved |
| Use Ground3D-LMM vs Reason3D | Ground3D-LMM · Reason3D dataset | mIoU: 31.20 -> 36.35 | Improved |
| Use Ground3D-LMM vs UniSeg3D | Ground3D-LMM · ScanRefer | mIoU: 29.10 -> 38.72 | Improved |
| Use 3D point input instead of image-only baseline for metric answers | Ground3D-LMM · Ground3D ScanNet text/metric | Mean APE: 166.91 -> 79.85 | Improved |
Closest papers by meaning
- SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models (CVPR 2025 · similarity 0.90)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.90)
- MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations (NeurIPS 2024 · similarity 0.89)
- Grounded 3D-Aware Spatial Vision-Language Modeling (CVPR 2026 · similarity 0.89)
- G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding (CVPR 2024 · similarity 0.89)
- Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis (CVPR 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.
