Research map / 3D vision / Face and shape
Towards Precise Completion of Deformable Shapes
Oshri Halimi, Ido Imanuel, Or Litany, Giovanni Trappolini, Emanuele Rodolà, Leonidas Guibas, Ron Kimmel
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 surface normals as input channels (ablation) | Ours · FAUST | relative improvement: 4.6% | Improved |
| add surface normals in the loss only (ablation) | Ours · FAUST | relative improvement: -3.3% | Hurt |
| add surface normals in both input and loss (ablation) | Ours · FAUST | relative improvement: 13% | Improved |
| replace Litany et al. with the proposed Siamese autoencoder | Litany et al. · FAUST projections (single-view completion) | Euclidean distance error: 7.07 -> 2.94 | Improved |
| replace Litany et al. with the proposed method | Litany et al. · FAUST projections (single-view completion) | Full Chamfer: 5.74 -> 4.37 | Improved |
| replace Litany et al. with the proposed method | Litany et al. · FAUST projections (single-view completion) | Volumetric error: 9.24 -> 7.05 | Improved |
| replace FARM with the proposed method | FARM · AMASS projections (single-view completion) | Euclidean distance error: 27.75 -> 6.58 | Improved |
| replace FARM with the proposed method | FARM · AMASS projections (single-view completion) | Full Chamfer: 16.31 -> 7.92 | Improved |
| replace 3D-CODED with the proposed method | 3D-CODED · AMASS projections (single-view completion) | Euclidean distance error: 36.14 -> 6.58 | Improved |
| replace 3D-CODED fixed-template deformation with the proposed method | 3D-CODED · FAUST projections (single-view completion) | Full Chamfer: 49.64 -> 4.37 | 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.
- 3D-CODED — 3D-CODED: 3D Correspondences by Deep Deformation (ECCV 2018) · better on 7 of 7 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
- Deformable Shape Completion With Graph Convolutional Autoencoders (CVPR 2018 · similarity 0.89)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.87)
- Partial-to-Partial Shape Matching with Geometric Consistency (CVPR 2024 · similarity 0.86)
- Learning Generalizable Shape Completion with SIM(3) Equivariance (NeurIPS 2025 · similarity 0.86)
- Point-based Instance Completion with Scene Constraints (ICLR 2025 · similarity 0.86)
- FSC: Few-point Shape Completion (CVPR 2024 · 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.
