Research map / 3D vision / Face and shape
Diffusion-SDF: Text-To-Shape via Voxelized Diffusion
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 Diffusion-SDF instead of AutoSDF | Text-to-shape generation · Text2Shape chairs | IoU: 0.187 -> 0.194 | Helped |
| use Diffusion-SDF instead of AutoSDF | Text-to-shape generation · Text2Shape chairs | Acc: 83.88 -> 88.56 | Helped |
| use Diffusion-SDF instead of AutoSDF | Text-to-shape generation · Text2Shape chairs | CLIP-S: 29.10 -> 30.88 | Helped |
| use Diffusion-SDF instead of AutoSDF | Text-to-shape generation · Text2Shape chairs | TMD: 0.581 -> 0.169 | Helped |
| replace U-Net with UinU-Net (ablation) | Diffusion-SDF · Text2Shape chairs | IoU: 0.187 -> 0.194 | Helped |
| replace U-Net with UinU-Net (ablation) | Diffusion-SDF · Text2Shape chairs | Acc: 80.98 -> 88.56 | Helped |
| replace U-Net with UinU-Net (ablation) | Diffusion-SDF · Text2Shape chairs | CLIP-S: 29.35 -> 30.88 | Helped |
| replace U-Net with UinU-Net (ablation) | Diffusion-SDF · Text2Shape chairs | TMD: 0.171 -> 0.169 | Helped |
| add inner-outer concatenation (ablation) | UinU-Net · Text2Shape chairs | IoU: 0.198 -> 0.194 | Hurt |
| add inner-outer concatenation (ablation) | UinU-Net · Text2Shape chairs | Acc: 83.91 -> 88.56 | Helped |
| add inner-outer concatenation (ablation) | UinU-Net · Text2Shape chairs | CLIP-S: 28.68 -> 30.88 | Helped |
| add inner-outer concatenation (ablation) | UinU-Net · Text2Shape chairs | TMD: 0.181 -> 0.169 | Hurt |
Closest papers by meaning
- Mosaic-SDF for 3D Generative Models (CVPR 2024 · similarity 0.89)
- PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion (CVPR 2024 · similarity 0.88)
- DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors (CVPR 2024 · similarity 0.88)
- Generating Images with 3D Annotations Using Diffusion Models (ICLR 2024 · similarity 0.88)
- Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation (ICLR 2025 · similarity 0.87)
- DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation (ICLR 2024 · 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.