Research map / 3D vision / Face and shape
CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model
Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, Jun Zhu
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 random resizing to multi-view diffusion training (ablation) | ImageDream 6-view + Zero-SNR · GSO subset novel view synthesis | PSNR: 29.13 -> 29.36 | Improved |
| add Zero-SNR training to multi-view diffusion (ablation) | ImageDream 6-view · GSO subset novel view synthesis | PSNR: 28.99 -> 29.13 | Improved |
| add contour augmentation to multi-view diffusion training (ablation) | ImageDream 6-view + Zero-SNR + resizing · GSO subset novel view synthesis | PSNR: 29.36 -> 28.92 | Hurt |
| add canonical coordinate map (CCM) input to the reconstruction U-Net (ablation) | CRM reconstruction model · qualitative geometry | geometry quality (qualitative) | Improved |
| use convolutional U-Net with six orthographic inputs instead of transformer (LRM) for triplane | CRM · GSO geometry | Chamfer Distance: 0.0168 -> 0.0094 | Improved |
| use convolutional U-Net with spatial prior instead of transformer | CRM · reconstruction training cost | training cost | Improved |
| CRM versus Wonder3D on F-score | CRM · GSO geometry | F-score (%): 76.75 -> 79.38 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SyncDreamer — SyncDreamer: Generating Multiview-consistent Images from a Single-view Image (ICLR 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
- Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers (CVPR 2024 · similarity 0.87)
- GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement (ICLR 2025 · similarity 0.86)
- One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion (CVPR 2024 · similarity 0.86)
- Large-Vocabulary 3D Diffusion Model with Transformer (ICLR 2024 · similarity 0.85)
- Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation (ICML 2025 · similarity 0.85)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 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.
