Research map / 3D vision / Face and shape
Diffusion-Based Signed Distance Fields for 3D Shape Generation
Jaehyeok Shim, Changwoo Kang, Kyungdon Joo
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 |
|---|---|---|---|
| Use SDF-Diffusion instead of PVD* for multi-category generation | ShapeNet 13-category generation · ShapeNet 13-category average | 1-NNA (CD): 61.48 -> 59.16 | Improved |
| Use SDF-Diffusion instead of PVD* for multi-category generation | ShapeNet 13-category generation · ShapeNet 13-category average | 1-NNA (EMD): 59.12 -> 55.96 | Improved |
| Use SDF-Diffusion instead of point-cloud baselines | single-category shape generation · ShapeNet Airplane | MMD (EMD): 1.55 -> 1.49 | Improved |
| Use SDF-Diffusion instead of point-cloud baselines | single-category shape generation · ShapeNet Airplane | 1-NNA (EMD): 52.72 -> 48.14; 47.40 -> 48.14 | Mixed |
| Use SDF-Diffusion instead of point-cloud baselines | single-category shape generation · ShapeNet Car | COV (EMD): 48.33 -> 52.47 | Improved |
| Use SDF-Diffusion instead of point-cloud baselines | single-category shape generation · ShapeNet Chair | 1-NNA (EMD): 53.03 -> 51.77; 48.74 -> 51.77 | Mixed |
| Represent generated shapes as SDF voxels and reconstruct meshes before point sampling | SDF-Diffusion · ShapeNet single-category generation | 1-NNA (EMD) | Mixed |
| Split generation into low-resolution synthesis followed by conditional patch-based super-resolution | SDF-Diffusion · ShapeNet 3D shape generation | generation quality | Improved |
Closest papers by meaning
- Mosaic-SDF for 3D Generative Models (CVPR 2024 · similarity 0.90)
- GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors (CVPR 2024 · similarity 0.89)
- Make-A-Shape: a Ten-Million-scale 3D Shape Model (ICML 2024 · similarity 0.89)
- UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion (CVPR 2024 · similarity 0.88)
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape (ICLR 2024 · similarity 0.88)
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior (CVPR 2024 · similarity 0.88)
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.
