Research map / 3D vision / 3D generation
Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations
Junyi Zhang, Yiming Wang, Yunhong Lu, Qichao Wang, Wenzhe Qian, Xiaoyin Xu, David Gu, Min Zhang
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 |
|---|---|---|---|
| add geometric regularization (normal, Laplacian, edge losses) to the geometry VQVAE (ablation) | geometry VQVAE · FaceScape reconstruction (30k steps) | Chamfer Distance (mm): 0.810 -> 0.666 | Improved |
| add Center-symmetric Padding instead of zero padding (ablation) | geometry VQVAE · qualitative (Fig. 5) | geometric cracks | Improved |
| increase DDIM inversion steps from 100 to 600 (ablation) | reconstruction · FaceScape reconstruction | Chamfer Distance (mm): 1.235 -> 0.465 | Improved |
| increase inversion steps beyond 600 (ablation) | reconstruction · FaceScape reconstruction | Chamfer Distance (mm): 0.465 -> 0.466 (1000 steps) | No clear effect |
| sphere-anchored SGR geometry vs implicit-function (ImFace++) reconstruction | face reconstruction · FaceScape reconstruction | Aspect Ratio: 4.34 -> 1.35 | Improved |
| native latent diffusion vs SDS-based text-to-3D methods | text-to-3D face · Describe3D prompts | inference time (min): 85 m (HumanNorm) -> 0.2 m | Improved |
| SGR diffusion vs FacialGAN on diversity | conditional geometry generation · FaceScape/COMA | DIV: 0.96 (FacialGAN) vs 0.93 (Ours) | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ImFace++ — ImFace: A Nonlinear 3D Morphable Face Model With Implicit Neural Representations (CVPR 2022) · better on 3 of 3 shared results
- HumanNorm — HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation (CVPR 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model (AAAI 2024 · similarity 0.89)
- Text-Guided 3D Face Synthesis - From Generation to Editing (CVPR 2024 · similarity 0.88)
- Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation (ICLR 2025 · similarity 0.88)
- Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres (ICML 2025 · similarity 0.86)
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior (CVPR 2024 · similarity 0.86)
- Spherical Manifold Guided Diffusion Model for Panoramic Image Generation (CVPR 2025 · 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.
