Skip to content
ModelListedExternal
Download

CRM

Model card for CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model.

KindOtherVersionRevision 36283fd

Model source

Kind
Other
File size
454 MB–5.74 GB
Version
vRevision 36283fd
Updated
Sep 21, 2026
Downloads
0
Source
Hugging Face

Source description

Convolutional Reconstruction Model

Model card for CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model.

Project Page: https://ml.cs.tsinghua.edu.cn/~zhengyi/CRM/

Arxiv: https://arxiv.org/abs/2403.05034

image/jpeg

The model contains a diffusion model to generate multi-view images from single input image, another difffusion to generate CCMs, and a UNet-based reconstruction model to get the final textured mesh.

Citation

@article{wang2024crm,
  title={CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model},
  author={Zhengyi Wang and Yikai Wang and Yifei Chen and Chendong Xiang and Shuo Chen and Dajiang Yu and Chongxuan Li and Hang Su and Jun Zhu},
  journal={arXiv preprint arXiv:2403.05034},
  year={2024}
}

Sources

1 source
Hugging FacePrimaryVersion 36283fd567b9a3120a166dfe2f2e0965d96261b0
huggingface.co/Zhengyi/CRM/tree/36283fd567b9a3120a166dfe2f2e0965d96261b0

Verified Sep 8

Model artifacts

3 artifacts

ccm-diffusion.pth

pth · 5.74 GB · SHA-256 220907ea252a…9861 · Hugging Face

Download

CRM.pth

pth · 454 MB · SHA-256 71fcf063f0be…3537 · Hugging Face

Download

pixel-diffusion.pth

pth · 5.74 GB · SHA-256 27445c0202f5…71e0 · Hugging Face

Download

Source excerpts

2 excerpts

--- license: mit pipeline_tag: image-to-3d tags: - image-to-3d --- # Convolutional Reconstruction Model Model card for *CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model*. Project Page: https://ml.cs.tsinghua.edu.cn/~zhengyi/CRM/ Arxiv: https://arxiv.org/abs/2403.05034 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/634e15aec1ce28f1de91c470/4Ggn8Vl8zV0kccAF1376o.jpeg) The model contains a diffusion model to generate multi-view images from single input image, another difffusion to generate CCMs, and a UNet-based reconstruction model to get the final textured mesh. ## Citation ``` @article{wang2024crm, title={CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model}, author={Zhengyi Wang and Yikai Wang and Yifei Chen and Chendong Xiang and Shuo Chen and Dajiang Yu and Chongxuan Li and Hang Su and Jun Zhu}, journal={arXiv preprint arXiv:2403.05034}, year={2024} } ```

Source context: 0 downloads · 61 likes · Pipeline image-to-3d · Repo Zhengyi/CRM