Research map / Point clouds / Segmentation and detection
SegPoint: Segment Any Point Cloud via Large Language Model
Shuting He, Henghui Ding, Xudong Jiang, Bihan Wen
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 Geometric Enhancer Module (KPConv-based local geometry injected via gated cross-attention) (ablation) | SegPoint vanilla baseline · Instruct3D val | mIoU: 16.1 -> 21.4 | Improved |
| add Geometric Enhancer Module (ablation) | SegPoint vanilla baseline · ScanRefer | mIoU: 30.3 -> 35.8 | Improved |
| add Geometric-guided Feature Propagation (ablation) | SegPoint vanilla baseline · Instruct3D val | mIoU: 16.1 -> 23.2 | Improved |
| add Geometric-guided Feature Propagation (ablation) | SegPoint vanilla baseline · ScanRefer | mIoU: 30.3 -> 38.1 | Improved |
| combine GEM and GFP (ablation) | SegPoint · Instruct3D val | mIoU: 23.2 -> 27.5 | Improved |
| use GEM instead of full fine-tuning of point encoder (ablation) | SegPoint · Instruct3D val | mIoU: 26.2 -> 27.5 | Improved |
| use GEM instead of LoRA adaptation (ablation) | SegPoint · Instruct3D val | mIoU: 24.8 -> 27.5 | Improved |
| use LLM-based unified model versus two-stage and single-stage specialist methods | SegPoint · Instruct3D val | mIoU: 12.8 -> 27.5 | Improved |
| unified LLM model compared with specialist semantic segmentation methods | SegPoint · ScanNet val | mIoU: 75.7 -> 74.1 | No clear effect |
Later papers that compared with this method
2 later accepted papers report SegPoint as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- MR-COSMO: Visual-Text Memory Recall and Direct CrOSs-MOdal Alignment Method for Query-Driven 3D Segmentation (AAAI 2026 · better on 3 of 3 shared results)
- MORE-STEM: Long-Short MemOry REcall and Spatio-TEmporal Consistency Model for Query-Driven 3D/4D Point Cloud Segmentation (CVPR 2026 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- OctFormer — OctFormer: Efficient Octree-Based Transformer for Point Cloud Compression with Local Enhancement (AAAI 2023) · better on 1 of 2 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
- All in One: Visual-Description-Guided Unified Point Cloud Segmentation (ICCV 2025 · similarity 0.88)
- COS3D: Collaborative Open-Vocabulary 3D Segmentation (NeurIPS 2025 · similarity 0.87)
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (ICLR 2024 · similarity 0.87)
- ReferSplat: Referring Segmentation in 3D Gaussian Splatting (ICML 2025 · similarity 0.87)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.87)
- LESS: Label-Efficient and Single-Stage Referring 3D Segmentation (NeurIPS 2024 · similarity 0.87)
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.
