Research map / 3D vision / Face and shape
Completing 3D Partial Assemblies with View-Consistent 2D-3D Correspondence
Weihao Wang, Yu Lan, Mingyu You, Bin He
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 translation loss (ablation) | image-guided assembly completion · PartNet Chair, Medium | Match Accuracy (MA): 38.05 -> 49.43 | Improved |
| add rotation loss (ablation) | image-guided assembly completion · PartNet Chair, Medium | Match Accuracy (MA): 46.43 -> 49.43 | Improved |
| add Chamfer shape loss (ablation) | image-guided assembly completion · PartNet Chair, Medium | Match Accuracy (MA): 42.84 -> 49.43 | Improved |
| add symmetry loss (ablation) | image-guided assembly completion · PartNet Chair, Medium | Match Accuracy (MA): 44.47 -> 49.43 | Improved |
| add auxiliary image guidance (ablation) | image-guided assembly completion · PartNet Chair, Medium | Match Accuracy (MA): 34.68 -> 49.43 | Improved |
| add auxiliary image guidance (ablation) | image-guided assembly completion · PartNet Chair, Medium | CCD (x10^-2): 0.69 -> 0.99 | Hurt |
| add self-supervised view alignment (ablation) | image-guided assembly completion · PartNet Chair, Medium | Match Accuracy (MA): 39.04 -> 49.43 | Improved |
| add missing discovery differential attention (ablation) | image-guided assembly completion · PartNet Chair, Medium | Match Accuracy (MA): 38.53 -> 49.43 | Improved |
| add autoregressive learning (ablation) | image-guided assembly completion · PartNet Chair, Medium | Match Accuracy (MA): 46.12 -> 49.43 | Improved |
| add view alignment (ablation) | image-guided assembly completion · PartNet Chair, Medium | CCD (x10^-2): 1.47 -> 0.99 | Improved |
| image-guided method vs FiT without part segmentation | Ours · PartNet Chair, Hard | Match Accuracy (MA): 22.26 -> 35.64 | Improved |
Closest papers by meaning
- Imagine: Image-Guided 3D Part Assembly with Structure Knowledge Graph (AAAI 2025 · similarity 0.89)
- Neural Assembler: Learning to Generate Fine-Grained Robotic Assembly Instructions from Multi-View Images (AAAI 2025 · similarity 0.87)
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.86)
- DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models (NeurIPS 2026 · similarity 0.86)
- 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition (NeurIPS 2024 · similarity 0.86)
- Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation (CVPR 2025 · similarity 0.86)
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.
