CRM

CRM (Convolutional Reconstruction Model) is Tsinghua University's image-to-3D model. Two multi-view diffusion models generate six views of the object and their coordinate maps, a convolutional UNet turns them into a triplane, and FlexiCubes extracts a coloured mesh. LibreYOLO runs it in plain PyTorch through the LibreGen factory.

Tasks
3d generation
Install
pip install "libreyolo[gen]"
Support tier
Sibling tier, since v1.8.0. A separate product surface with its own factory and contract.
Upstream
CRM by Tsinghua University (TSAIL), CreativeML OpenRAIL++-M. Paper, source
Licenses
Code MIT and Apache-2.0, weights CreativeML OpenRAIL++-M. Commercial use

Install

bash
pip install "libreyolo[gen]"

texture=True also needs the MIT-licensed xatlas package (pip install xatlas) for the UV unwrap.

Predict

Nothing is gated and no login is needed. Weights download on first use from LibreYOLO/LibreCRM at a pinned revision.

Python
from libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("crm")             # weights download on first useresult = model(SAMPLE_IMAGE, seed=0) result.save("object.obj")           # vertex colours as `v x y z r g b`m = result.meshesprint(m.vertices[0].shape, m.extras["vertex_colors"][0].shape)
CLI
# Saves the object as .obj under runs/generate/predict.libreyolo generate source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/guggenheim-bilbao.jpg model=crm seed=0libreyolo generate source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/guggenheim-bilbao.jpg model=crm texture=true
Texture
# pip install xatlas   (MIT, for the UV unwrap)from libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("crm")model(SAMPLE_IMAGE, texture=True).save("object.obj")# writes object.obj, object.mtl and object_texture.png

Two multi-view diffusion models generate six orthographic views of the object and then their canonical coordinate maps; a convolutional UNet turns them into a triplane, and FlexiCubes extracts a mesh coloured by the triplane. Upstream needs xformers, nvdiffrast (NVIDIA, non-commercial) and a GPL mesh library; LibreYOLO runs the same weights in plain PyTorch on NVIDIA GPUs, Apple silicon and CPU, in fp16 on the GPUs as upstream.

The input is padded to a square on grey, without a crop, so a photo works best with the object filling the frame. A seed gives the same starting noise on every device; on CUDA a repeat call gives the same views and triangles, with vertices that can move by about 1e-7. The library measured about 12 s and 12 GB per object on an RTX 3090.

result.meshes holds vertices (V, 3), z-up in [-0.5, 0.5]^3, faces (F, 3) and extras["vertex_colors"] (V, 3) RGB in [0, 1]. texture=True bakes a 1024 x 1024 UV texture, as upstream does.

Settings

SettingDefaultMeaning
steps50Sampling steps of both diffusion stages, 1 to 499.
guidance5.0Classifier-free guidance of both stages.
textureFalseBake a UV texture (.mtl and .png beside the .obj).

Variants

One checkpoint, 4.1B parameters: two 2.0B multi-view diffusion models (UNet, OpenCLIP ViT-H/14 and SD VAE each) and a 0.12B reconstruction UNet. About 12.8 GB, plus 0.4 GB for BiRefNet.

Export

TaskONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
3D generation3D generation to ONNX: not supported3D generation to TorchScript: not supported3D generation to ExecuTorch: not supported3D generation to TensorRT: not supported3D generation to OpenVINO: not supported3D generation to Paddle: not supported3D generation to MNN: not supported3D generation to RKNN: not supported3D generation to Axelera: not supported3D generation to ncnn: not supported3D generation to TFLite: not supported3D generation to CoreML: not supported3D generation to Core AI: not supported

Export is not implemented for LibreGen 3D families. export(), train() and val() raise NotImplementedError (ADR 0031 in the library).

Licensing

Check the license on the Hugging Face repository of the specific weights you download. Every checkpoint in the LibreYOLO org carries one, and they are not always the same across a family. That repository is the authoritative source; the summary below describes what applied when this page was last verified.

This is a description of the licenses involved, not legal advice. If the answer matters commercially, read the licenses yourself and take your own counsel.

Original work
CRM, Tsinghua University (TSAIL)
Upstream license
CreativeML OpenRAIL++-M
Upstream source
github.com/thu-ml/CRM
LibreYOLO code
MIT
Weights
CreativeML OpenRAIL++-M, republished at huggingface.co/LibreYOLO
Interpretation
The CRM code is MIT and its model card declares MIT for the weights, but CRM's two diffusion models are fine-tuned from ImageDream and MVDream, themselves from Stable Diffusion 2.1, so LibreYOLO treats the weights as under the CreativeML OpenRAIL++-M License of that lineage. OpenRAIL++-M allows commercial use, but its use-based restrictions (no illegal, harmful, discriminatory or deceptive uses, among others) bind you and must be passed on to anyone you share the model or derivatives with. LibreYOLO's adapter is MIT; the code it adapts from CRM is MIT, the FlexiCubes meshing comes from NVIDIA's Apache-2.0 release, and ImageDream parts are Apache-2.0, noted in libreyolo/models/gen/crm/NOTICE. CRM's own FlexiCubes copies with NVIDIA's all-rights-reserved header, nvdiffrast (non-commercial) and the GPL-3.0 mesh tools upstream calls are not used. The Zhengyi/CRM weights are redistributed unchanged as LibreYOLO/LibreCRM, whose card carries the OpenRAIL++-M terms; Background removal runs on LibreYOLO's BiRefNet port with the ZhengPeng7/BiRefNet weights (MIT), from LibreYOLO/LibreTRELLISl. Both are pinned and not gated.

CRM is by Tsinghua University (TSAIL) (thu-ml/CRM). The code is MIT and the model card declares MIT for the weights.

The weights carry use restrictions. CRM's two diffusion models descend from ImageDream, MVDream and Stable Diffusion 2.1, so LibreYOLO treats them as under the CreativeML OpenRAIL++-M License of that lineage. Commercial use is allowed, but its use-based restrictions (no illegal, harmful, discriminatory or deceptive uses, among others) bind you and must be passed on to anyone you share the model or derivatives with.

The Zhengyi/CRM weights are redistributed unchanged as LibreYOLO/LibreCRM, whose card carries the OpenRAIL++-M terms. FlexiCubes comes from NVIDIA's Apache-2.0 release; nvdiffrast and the GPL-3.0 mesh tools upstream calls are not used.

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}
}

Copied from the authors' citation block at github.com/thu-ml/CRM#citation.

Verified against LibreYOLO v1.8.0. Support tables, checkpoints and benchmark numbers on this page are generated from the released library and the published weights, not written by hand.