Research map / 3D vision / Face and shape
Deformable Shape Completion With Graph Convolutional Autoencoders
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 closest-vertex correspondence refinement when SGD plateaus (ablation) | Shape completion using MoNet correspondences · Synthetic range scans completion | Euclidean distance [cm]: 3.40 -> 2.84 | Helped |
| Add closest-vertex correspondence refinement when SGD plateaus (ablation) | Shape completion using MoNet correspondences · Synthetic range scans completion | Volumetric error mean ± std [%]: 12.51 ± 11.1 -> 9.24 ± 8.62 | Helped |
| Cap optimization at 300 steps rather than running until convergence (ablation) | Shape completion using MoNet correspondences with refinement · Synthetic range scans completion | Euclidean distance [cm]: 3.01 -> 2.84 | Hurt |
| Use ground-truth correspondences instead of MoNet correspondences (ablation) | Shape completion · Synthetic range scans completion | Euclidean distance [cm]: 3.40 -> 2.51 | Helped |
| Fuse three completed views by averaging their latent variables | Shape completion · FAUST shape fusion, three partial views (first row) | Euclidean error [cm]: 2.78, 2.94, 2.93 -> 2.59 | Helped |
| Fuse three completed views by averaging their latent variables | Shape completion · FAUST shape fusion, three partial views (second row) | Euclidean error [cm]: 3.03, 3.39, 2.73 -> 2.61 | Helped |
Closest papers by meaning
- Variational Autoencoders for Deforming 3D Mesh Models (CVPR 2018 · similarity 0.90)
- ShapeFormer: Transformer-Based Shape Completion via Sparse Representation (CVPR 2022 · similarity 0.89)
- Learning 3D Shape Completion From Laser Scan Data With Weak Supervision (CVPR 2018 · similarity 0.89)
- Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion (CVPR 2020 · similarity 0.89)
- Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis (CVPR 2017 · similarity 0.89)
- Learning Generalizable Shape Completion with SIM(3) Equivariance (NeurIPS 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.