Research map / 3D vision / Face and shape
CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism
Jiahui Lei, Kostas Daniilidis
Check 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 |
|---|---|---|---|
| replace the invertible canonical map with a one-way MLP (ablation) | CaDeX · DT4D-A deer, PCL | IoU: 66.5% -> 61.9% | Hurt |
| replace the invertible canonical map with a one-way MLP (ablation) | CaDeX · DT4D-A deer, PCL | CD: 0.128 -> 0.161 | Hurt |
| remove the canonical-space geometry encoder (ablation) | CaDeX · DT4D-A deer, PCL | IoU: 66.5% -> 63.4% | Hurt |
| use NICE instead of NVP to conserve volume (ablation) | CaDeX on D-FAUST · D-FAUST, seen individual, with correspondence supervision | IoU: 89.1% -> 85.4% | Hurt |
| use the per-frame PF encoder instead of the ST encoder (ablation) | CaDeX on D-FAUST · D-FAUST, seen individual, with correspondence supervision | IoU: 86.7% -> 89.1% | 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.
- A-SDF — A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation (ICCV 2021) · better on 2 of 2 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
- Neural Shape Deformation Priors (NeurIPS 2022 · similarity 0.88)
- Topologically-Aware Deformation Fields for Single-View 3D Reconstruction (CVPR 2022 · similarity 0.88)
- Neural Cages for Detail-Preserving 3D Deformations (CVPR 2020 · similarity 0.87)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.86)
- Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis (CVPR 2025 · similarity 0.86)
- Implicit Neural Surface Deformation with Explicit Velocity Fields (ICLR 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.
