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.
- Aufgaben
- 3d generation
- Installation
pip install "libreyolo[gen]"- Supportstufe
- Geschwisterstufe, seit v1.8.0. Eine separate Produktoberfläche mit eigener Factory und eigenem Vertrag.
- Upstream
- CRM von Tsinghua University (TSAIL), CreativeML OpenRAIL++-M. Publikation, Quelle
- Lizenzen
- Code MIT and Apache-2.0, Gewichte CreativeML OpenRAIL++-M. Kommerzielle Nutzung
Install
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.
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)# 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# 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.pngTwo 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
| Setting | Default | Meaning |
|---|---|---|
steps | 50 | Sampling steps of both diffusion stages, 1 to 499. |
guidance | 5.0 | Classifier-free guidance of both stages. |
texture | False | Bake 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
| Aufgabe | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3D generation | 3D generation to ONNX: nicht unterstützt | 3D generation to TorchScript: nicht unterstützt | 3D generation to ExecuTorch: nicht unterstützt | 3D generation to TensorRT: nicht unterstützt | 3D generation to OpenVINO: nicht unterstützt | 3D generation to Paddle: nicht unterstützt | 3D generation to MNN: nicht unterstützt | 3D generation to RKNN: nicht unterstützt | 3D generation to Axelera: nicht unterstützt | 3D generation to ncnn: nicht unterstützt | 3D generation to TFLite: nicht unterstützt | 3D generation to CoreML: nicht unterstützt | 3D generation to Core AI: nicht unterstützt |
Export is not implemented for LibreGen 3D families. export(), train() and
val() raise NotImplementedError (ADR 0031 in the library).
Licensing
Prüfe die Lizenz im Hugging-Face-Repository der konkreten Gewichte, die du herunterlädst. Jeder Checkpoint in der LibreYOLO-Organisation hat eine Lizenz, und sie ist innerhalb einer Familie nicht immer gleich. Dieses Repository ist die maßgebliche Quelle. Die Zusammenfassung unten beschreibt den Stand bei der letzten Verifizierung dieser Seite.
Dies ist eine Beschreibung der beteiligten Lizenzen und keine Rechtsberatung. Wenn die Antwort kommerziell relevant ist, lies die Lizenzen selbst und hole eigenen Rechtsrat ein.
- Originalarbeit
- CRM, Tsinghua University (TSAIL)
- Upstream-Lizenz
- CreativeML OpenRAIL++-M
- Upstream-Quelle
- github.com/thu-ml/CRM
- LibreYOLO-Code
- MIT
- Gewichte
- CreativeML OpenRAIL++-M, erneut unter huggingface.co/LibreYOLO veröffentlicht
- Einordnung
- 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}
}Aus dem Zitierblock der Autoren unter github.com/thu-ml/CRM#citation kopiert.