Research map / 3D vision / Face and shape
Semantic-Aware Implicit Template Learning via Part Deformation Consistency
Sihyeon Kim, Minseok Joo, Jaewon Lee, Juyeon Ko, Juhan Cha, Hyunwoo J. Kim
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 |
|---|---|---|---|
| use soft instead of hard assignment of part deformation priors (ablation) | semantic-aware deformation code · ShapeNet chair 5-shot part label transfer | mIoU: 77.0 -> 84.2 | Improved |
| add global deformation consistency (Chamfer) to part deformation consistency (ablation) | regularization · ShapeNet chair 5-shot PLT | mIoU: 83.4 -> 83.9 | Improved |
| add global scale consistency regularization (ablation) | regularization · ShapeNet chair 5-shot PLT | mIoU: 83.9 -> 84.2 | Improved |
| use only part deformation consistency losses (ablation) | regularization · ShapeNet chair 5-shot PLT | mIoU: 80.4/82.1 (DIT/DIF) -> 83.4 | Improved |
| vary BAE-Net part count k from 2 to 10 (ablation) | semantic prior · ShapeNet chair 5-shot PLT | mIoU: 82.8 to 83.8 across k | No clear effect |
| semantic-aware deformation and part consistency on high-variability categories | proposed framework vs DIF · KeypointNet chair PCK@0.1 | PCK: 57.6 -> 83.2 | Improved |
| semantic prior vs DIF in reconstruction of unseen table shapes | proposed framework · ShapeNet table reconstruction | Chamfer distance x10^3: 0.2640 -> 0.2796 | Hurt |
| semantic prior in 2-shot part label transfer across subcategories | proposed framework vs DIF · ShapeNet subcategories | mIoU: 64.5 -> 72.8 (airliner/jet); 66.3 -> 77.5 (straight/sofa) | Improved |
| use coarser semantic prior (RIM-Net level 1) instead of finer one (ablation) | semantic prior · ShapeNet chair subcategories 2-shot PLT | mIoU: 78.3 -> 70.1 | Hurt |
| apply method to non-rigid DFAUST | proposed framework vs DIF · DFAUST keypoint transfer | PCK@0.05 / 0.1: 67.0/80.7 -> 74.9/85.2 | Improved |
Closest papers by meaning
- Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects (ICCV 2023 · similarity 0.91)
- Deep Implicit Templates for 3D Shape Representation (CVPR 2021 · similarity 0.89)
- Deformed Implicit Field: Modeling 3D Shapes With Learned Dense Correspondence (CVPR 2021 · similarity 0.89)
- Implicit Modeling of Non-rigid Objects with Cross-Category Signals (AAAI 2024 · similarity 0.87)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.87)
- Implicit Neural Surface Deformation with Explicit Velocity Fields (ICLR 2025 · 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.
