Research map / 3D vision / 3D generation
3x2: 3D Object Part Segmentation by 2D Semantic Correspondences
Anh Thai, Weiyao Wang, Hao Tang, Stefan Stojanov, James M Rehg, Matt Feiszli
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 |
|---|---|---|---|
| generate non-overlapping masks from SAM proposals (ablation) | 3-By-2 2D segmentation · PartNetE few-shot (Scissors, Mouse, Suitcase, Bottle, Chair) | mIoU: 0.457 -> 0.675 (Scissors), 0.004 -> 0.810 (Bottle) | Improved |
| aggregate multi-view labels per mask instead of per point (ablation) | 3-By-2 3D aggregation · PartNetE few-shot (Scissors, Suitcase, Printer, Clock) | mIoU: 0.363 -> 0.458 (Clock), 0.009 -> 0.085 (Printer) | Improved |
| replace VLPart 2D segmenter with SAM plus DIFT label transfer (ablation) | 3-By-2 with mask-consistency aggregation · PartNetE zero-shot (PACO) | mIoU: 0.222 -> 0.430 | Improved |
| add more categories to the label database (ablation) | 3-By-2 · PartNetE Kettle | mIoU: 0.815 -> 0.757 -> 0.752 | Hurt |
| add Chair objects to Table database for wheel transfer (ablation) | 3-By-2 · PartNetE tables with wheels | mIoU: 0.411 -> 0.625 average; wheel 0.000 -> 0.600 | Improved |
| increase labeled instances in the database from 1 to 8 (ablation) | 3-By-2 · PartNetE Kettle | mIoU: 0.809 -> 0.815 | No clear effect |
| increase number of rendered views beyond 10 (ablation) | 3-By-2 · PartNetE | mIoU | No clear effect |
| use training-free label transfer instead of language-guided GLIP detection | PartSLIP · PartNet level-3 | mIoU: 0.125 -> 0.281 | Improved |
| 3-By-2 versus MvDeCor on fine-grained PartNet | MvDeCor · PartNet level-3 | mIoU: 0.277 -> 0.281 | No clear effect |
| sparse random pixel sampling for label transfer across runs (ablation) | 3-By-2 · PartNetE (Scissors, Kettle, Suitcase, Bottle) | mIoU std: std 0.002 to 0.008 | No clear effect |
| coarse-to-fine correspondence search (ablation) | 3-By-2 · 800x800 image pair | wall time speedup: approximately 2000 times | Improved |
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.
- MvDeCor — MvDeCor: Multi-View Dense Correspondence Learning for Fine-Grained 3D Segmentation (ECCV 2022) · better on 1 of 1 shared result
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
- PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding (CVPR 2019 · similarity 0.91)
- PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model (ECCV 2024 · similarity 0.90)
- PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding (NeurIPS 2025 · similarity 0.89)
- 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition (NeurIPS 2024 · similarity 0.88)
- BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis (CVPR 2025 · similarity 0.88)
- PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation (CVPR 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.
