Research map / 3D vision / Face and shape
Learning to Generate 3D Shapes with Generative Cellular Automata
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 |
|---|---|---|---|
| Use GCA instead of cGAN | probabilistic shape completion · PartNet (Avg.) | MMD: 1.65 -> 1.42 | Helped |
| Use GCA instead of cGAN-im-l2z | probabilistic shape completion · PartNet (Avg.) | TMD: 3.34 -> 6.20 | Helped |
| Use GCA instead of cGAN-im-pc2z | probabilistic shape completion · PartNet (Avg.) | UHD: 5.81 -> 5.92 | Hurt |
| Use GCA instead of cGAN | probabilistic shape completion · PartNet-Scan (Avg.) | MMD: 1.75 -> 1.70 | Helped |
| Use GCA instead of cGAN-im-l2z | probabilistic shape completion · PartNet-Scan (Avg.) | TMD: 3.93 -> 5.20 | Helped |
| Use GCA instead of cGAN-im-pc2z | probabilistic shape completion · PartNet-Scan (Avg.) | UHD: 6.18 -> 5.85 | Helped |
| Use GCA instead of ShapeGF | shape generation · ShapeNet (Avg.) | 1-NNA: 72.23 -> 74.85 | Hurt |
| Use GCA instead of ShapeGF | shape generation · ShapeNet (Avg.) | COV: 46.21 -> 40.79 | Hurt |
| Use GCA instead of ShapeGF | shape generation · ShapeNet (Avg.) | MMD: 6.73 -> 7.44 | Hurt |
| Train the transition kernel jointly across categories (ablation) | GCA · PartNet (Avg.) | MMD: 1.42 -> 1.45 | Hurt |
| Train the transition kernel jointly across categories (ablation) | GCA · PartNet (Avg.) | TMD: 6.20 -> 7.24 | Helped |
| Train the transition kernel jointly across categories (ablation) | GCA · PartNet (Avg.) | UHD: 5.92 -> 6.01 | Hurt |
Closest papers by meaning
- Make-A-Shape: a Ten-Million-scale 3D Shape Model (ICML 2024 · similarity 0.88)
- GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors (CVPR 2024 · similarity 0.86)
- ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion (CVPR 2025 · similarity 0.86)
- Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata (CVPR 2024 · similarity 0.86)
- Enhancing Implicit Shape Generators Using Topological Regularizations (ICML 2024 · similarity 0.85)
- Mosaic-SDF for 3D Generative Models (CVPR 2024 · similarity 0.85)
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.