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.

Tarefas
3d generation
Instalação
pip install "libreyolo[gen]"
Nível de suporte
Nível irmão, desde a v1.8.0. Uma superfície de produto separada, com sua própria fábrica e seu próprio contrato.
Origem
CRM por Tsinghua University (TSAIL), CreativeML OpenRAIL++-M. Artigo, código-fonte
Licenças
Código MIT and Apache-2.0, pesos CreativeML OpenRAIL++-M. Uso comercial

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

TarefaONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
3D generation3D generation to ONNX: incompatível3D generation to TorchScript: incompatível3D generation to ExecuTorch: incompatível3D generation to TensorRT: incompatível3D generation to OpenVINO: incompatível3D generation to Paddle: incompatível3D generation to MNN: incompatível3D generation to RKNN: incompatível3D generation to Axelera: incompatível3D generation to ncnn: incompatível3D generation to TFLite: incompatível3D generation to CoreML: incompatível3D generation to Core AI: incompatível

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

Licensing

Confira a licença no repositório do Hugging Face correspondente aos pesos que você baixar. Cada checkpoint na organização LibreYOLO tem uma licença, e ela nem sempre é a mesma em toda a família. Esse repositório é a fonte oficial. O resumo abaixo descreve o que se aplicava na última verificação desta página.

Esta é uma descrição das licenças envolvidas, não uma orientação jurídica. Se a resposta tiver importância comercial, leia as licenças e procure sua própria assessoria.

Trabalho original
CRM, Tsinghua University (TSAIL)
Licença original
CreativeML OpenRAIL++-M
Código-fonte original
github.com/thu-ml/CRM
Código do LibreYOLO
MIT
Pesos
CreativeML OpenRAIL++-M, republicado em huggingface.co/LibreYOLO
Interpretação
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}
}

Copiado do bloco de citação dos autores em github.com/thu-ml/CRM#citation.

Verificado com o LibreYOLO v1.8.0. As tabelas de suporte, os checkpoints e os números de benchmark desta página são gerados a partir da biblioteca lançada e dos pesos publicados, não escritos à mão.