Research map / Point clouds / Segmentation and detection
Spatial Matters: Position-Guided 3D Referring Expression Segmentation
Yabing Wang, Zhuotao Tian, Le Wang, Zheng Qin, Sanping Zhou
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 |
|---|---|---|---|
| build point proxies (local context plus spatial interaction) before query selection instead of using FPS key points directly (ablation) | Position3D · ScanRefer | mIoU: 48.2 -> 51.0 | Improved |
| add spatial relation modeling in query generation (ablation) | Position3D · ScanRefer | mIoU: 49.2 -> 51.0 | Improved |
| add spatial relation modeling in the decoder (ablation) | Position3D · ScanRefer | mIoU: 49.0 -> 51.0 | Improved |
| use progressively decreasing super-points {128,64,32,16} instead of all super-points (ablation) | position-guided deformable attention · ScanRefer | mIoU: 49.4 -> 51.0 | Improved |
| use constant 16 super-points per layer (ablation) | position-guided deformable attention · ScanRefer | mIoU: 51.0 -> 48.2 | Hurt |
| shrink super-points faster {128,64,16,8} (ablation) | position-guided deformable attention · ScanRefer | mIoU: 51.0 -> 50.3 | Hurt |
| use 8 nearest neighbors in local context aggregation (ablation) | Position3D · ScanRefer | mIoU: 51.0 -> 49.0 | Hurt |
| use 64 nearest neighbors in local context aggregation (ablation) | Position3D · ScanRefer | mIoU: 51.0 -> 49.5 | Hurt |
| Position3D vs IPDN on unique subset | Position3D · ScanRefer (Unique subset) | mIoU: 78.6 -> 77.6 | Hurt |
| Position3D vs IPDN on multiple subset | Position3D · ScanRefer (Multiple subset) | mIoU: 43.6 -> 44.7 | Improved |
| Position3D vs MDIN on zero-target with distractors | Position3D · Multi3DRefer (zero target with distractors) | Acc@0.25: 47.9 -> 45.5 | Hurt |
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.
- IPDN — IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation (AAAI 2025) · better on 8 of 9 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
- RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation (NeurIPS 2024 · similarity 0.92)
- ReferSplat: Referring Segmentation in 3D Gaussian Splatting (ICML 2025 · similarity 0.90)
- LESS: Label-Efficient and Single-Stage Referring 3D Segmentation (NeurIPS 2024 · similarity 0.90)
- IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation (AAAI 2025 · similarity 0.90)
- X-RefSeg3D: Enhancing Referring 3D Instance Segmentation via Structured Cross-Modal Graph Neural Networks (AAAI 2024 · similarity 0.89)
- 3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation (AAAI 2024 · 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.
