Research map / 3D vision / Face and shape
Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence
Ronghan Chen, Yang Cong, Jiahua Dong
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 Extrinsic-Intrinsic Autoencoder instead of global embedding (ablation) | UD2E-Net · SURREAL (230k) | C_De (cm): 2.23 -> 1.91 | Improved |
| add Extrinsic-Intrinsic Autoencoder instead of global embedding (ablation) | UD2E-Net · SURREAL (23k) | C_De (cm): 2.61 -> 2.04 | Improved |
| add bounded MMD loss (ablation) | UD2E-Net · SURREAL (230k) | C_De (cm): 2.47 -> 1.91 | Improved |
| add bounded MMD loss (ablation) | UD2E-Net · SURREAL (23k) | C_De (cm): 2.47 -> 2.04 | Improved |
| add trace and propagation instead of knn node assignment (ablation) | UD2E-Net · SURREAL (230k) | C_De (cm): 2.85 -> 1.91 | Improved |
| add trace and propagation instead of knn node assignment (ablation) | UD2E-Net · SURREAL (23k) | C_De (cm): 3.08 -> 2.04 | Improved |
| use 10D canonical shape instead of 3D (ablation) | UD2E-Net · SURREAL (230k) | C_De (cm): 2.02 -> 1.91 | Improved |
| set bounded MMD weight beta to 0.01 instead of 0 (ablation) | UD2E-Net · SURREAL (230k) | C_De (cm): 2.30 -> 1.91 | Improved |
| retrieve a similar template instead of a fixed one | UD2E-Net · SURREAL (23k) | R_Gt (cm): 1.78 -> 1.12 | Improved |
| retrieve a similar template instead of a fixed one | UD2E-Net · DFAUST | R_Gt (cm): 1.84 -> 1.752 | Improved |
| reduce SURREAL training data from 230k to 23k | 3D-CODED and Elementary · SURREAL | reconstruction error | Hurt |
| reduce SURREAL training data from 230k to 23k | UD2E-Net · SURREAL | reconstruction error | No clear effect |
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.
- 3D-CODED — 3D-CODED: 3D Correspondences by Deep Deformation (ECCV 2018) · better on 5 of 5 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
- Unsupervised Learning of Dense Shape Correspondence (CVPR 2019 · similarity 0.91)
- 3D-CODED: 3D Correspondences by Deep Deformation (ECCV 2018 · similarity 0.90)
- Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching (NeurIPS 2022 · similarity 0.88)
- Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects (ICCV 2023 · similarity 0.88)
- CorrNet3D: Unsupervised End-to-End Learning of Dense Correspondence for 3D Point Clouds (CVPR 2021 · similarity 0.88)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (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.
