Research map / 3D vision / Face and shape
AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation
Check 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 the non-sequential autoregressive shape prior for completion | AutoSDF · ShapeNet chairs, bottom half | UHD: 0.0627 -> 0.0567 | Helped |
| use the non-sequential autoregressive shape prior for completion | AutoSDF · ShapeNet chairs, bottom half | TMD: 0.0303 -> 0.0341 | Helped |
| use the non-sequential autoregressive shape prior for completion | AutoSDF · ShapeNet chairs, octant | UHD: 0.0536 -> 0.0599 | Hurt |
| use the non-sequential autoregressive shape prior for completion | AutoSDF · ShapeNet chairs, octant | TMD: 0.0376 -> 0.0693 | Helped |
| use non-sequential instead of sequential autoregressive modeling (ablation) | AutoSDF · ShapeNet single-view reconstruction | IoU: 0.554 -> 0.577 | Helped |
| use non-sequential instead of sequential autoregressive modeling (ablation) | AutoSDF · ShapeNet single-view reconstruction | CD: 1.448 -> 1.331 | Helped |
| use non-sequential instead of sequential autoregressive modeling (ablation) | AutoSDF · ShapeNet single-view reconstruction | F-score: 0.393 -> 0.414 | Helped |
| use non-sequential instead of sequential autoregressive modeling (ablation) | AutoSDF · Pix3D single-view reconstruction | IoU: 0.516 -> 0.521 | Helped |
| use non-sequential instead of sequential autoregressive modeling (ablation) | AutoSDF · Pix3D single-view reconstruction | CD: 2.254 -> 2.267 | Hurt |
| use non-sequential instead of sequential autoregressive modeling (ablation) | AutoSDF · Pix3D single-view reconstruction | F-score: 0.412 -> 0.415 | Helped |
| combine the shape prior with language conditionals | AutoSDF · Language-guided generation | target preference: 18% -> 66% | Helped |
| combine the shape prior with language conditionals | AutoSDF · Language-guided generation | target preference: 23% -> 61% | Helped |
Closest papers by meaning
- Probabilistic Implicit Scene Completion (ICLR 2022 · similarity 0.90)
- Deep Optimized Priors for 3D Shape Modeling and Reconstruction (CVPR 2021 · similarity 0.90)
- AutoPartGen: Autoregressive 3D Part Generation and Discovery (NeurIPS 2025 · similarity 0.89)
- DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models (NeurIPS 2026 · similarity 0.88)
- SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE (CVPR 2025 · similarity 0.88)
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction (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.