Repository files navigation

Official PyTorch implementation of Metric3Dv1 and Metric3Dv2:

[1]Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image

[2]Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation

🏆Champion inCVPR2023 Monocular Depth Estimation Challenge

• [2024/8] Metric3Dv2 is accepted by TPAMI!
• [2024/7/5] Our stable-diffusion alternative GeoWizard has now been accepted by ECCV 2024! Check NOW therepository andpaper for the finest-grained geometry ever! 🎉🎉🎉
• [2024/6/25] Json files for KITTI datasets now available! Refer toTraining for more details
• [2024/6/3] ONNX is supported! We appreciate@xenova for their remarkable efforts!
• [2024/4/25] Weights for ViT-giant2 model released!
• [2024/4/11] Training codes are released!
• [2024/3/18]HuggingFace 🤗 GPU version updated!
• [2024/3/18]Project page released!
• [2024/3/18] Metric3D V2 models released, supporting metric depth and surface normal now!
• [2023/8/10] Inference codes, pre-trained weights, and demo released.
• [2023/7] Metric3D accepted by ICCV 2023!
• [2023/4] The Champion of2nd Monocular Depth Estimation Challenge in CVPR 2023

Metric3D is a strong and robust geometry foundation model for high-quality and zero-shotmetric depth andsurface normal estimation from a single image. It excels at solving in-the-wild scene reconstruction. It can directly help you measure the size of structures from a single image. Now it achieves SOTA performance on over 10 depth and normal benchmarks.

Our models rank 1st on the routing KITTI and NYU benchmarks.

Even compared to recent affine-invariant depth methods (Marigold and Depth Anything), our metric-depth (and normal) models still show superior performance.

Our models also show powerful performance on normal benchmarks.

For the ViT models, use the following environment：

pip install -r requirements_v2.txt

For ConvNeXt-L, it is

pip install -r requirements_v1.txt

With off-the-shelf depth datasets, we need to generate json annotaions in compatible with this dataset, which is organized by:

dict('files':list(dict('rgb': 'data/kitti_demo/rgb/xxx.png','depth': 'data/kitti_demo/depth/xxx.png','depth_scale': 1000.0 # the depth scale of gt depth img.'cam_in': [fx, fy, cx, cy],),dict(...),...))

To generate such annotations, please refer to the "Inference" section.

Inmono/configs we provide different config setups.

Intrinsics of the canonical camera is set bellow:

    canonical_space = dict(        img_size=(512, 960),        focal_length=1000.0,    ),

where cx and cy is set to be half of the image size.

Inference settings are defined as

    depth_range=(0, 1),    depth_normalize=(0.3, 150),    crop_size = (512, 1088),

where the images will be first resized as thecrop_size and then fed into the model.

Please refer totraining/README.md.Now we provide complete json files for KITTI fine-tuning.

Now the onnx supports are availble for all three models with varying shapes. Refer toissue117 for more details.

One additionalreminder for using these onnx models is reported by @norbertlink.

Now you can use Metric3D via Pytorch Hub with just few lines of code:

importtorchmodel=torch.hub.load('yvanyin/metric3d','metric3d_vit_small',pretrain=True)pred_depth,confidence,output_dict=model.inference({'input':rgb})pred_normal=output_dict['prediction_normal'][:, :3, :, :]# only available for Metric3Dv2 i.e., ViT modelsnormal_confidence=output_dict['prediction_normal'][:,3, :, :]# see https://arxiv.org/abs/2109.09881 for details

Supported models:metric3d_convnext_tiny,metric3d_convnext_large,metric3d_vit_small,metric3d_vit_large,metric3d_vit_giant2.

We also provided a minimal working example inhubconf.py, which hopefully makes everything clearer.

We also provided a flexible working example inmetric3d_onnx_export.py to export the Pytorch Hub model to ONNX format. We could test with the following commands:

# Export the model to ONNX modelpython3 onnx/metric_3d_onnx_export.py metric3d_vit_small# metric3d_vit_large/metric3d_convnext_large# Test the inference of the ONNX modelpython3 onnx/test_onnx.py metric3d_vit_small.onnx

ros2_vision_inference provides a Python example, showcasing a pipeline from image to point clouds and integrated into ROS2 systems.

1. put the trained ckpt filemodel.pth inweight/.
2. generate data annotation by following the codedata/gene_annos_kitti_demo.py, which includes 'rgb', (optional) 'intrinsic', (optional) 'depth', (optional) 'depth_scale'.
3. change the 'test_data_path' intest_*.sh to the*.json path.
4. runsource test_kitti.sh orsource test_nyu.sh.

1. put the trained ckpt filemodel.pth inweight/.
2. change the 'test_data_path' intest.sh to the image folder path.
3. runsource test_vit.sh for transformers andsource test.sh for convnets.As no intrinsics are provided, we provided by default 9 settings of focal length.

If you are interested in combining metric3D and monocular visual slam system to achieve the metric slam, you can refer to thisrepo.

Because the focal length is not properly set! Please find a proper focal length by modifying codeshere yourself.

Because the images are too large! Use smaller ones instead.

First be sure all black padding regions at image boundaries are cropped out. Then please try again.Besides, metric 3D is not almighty. Some objects (chandeliers, drones...) / camera views (aerial view, bev...) do not occur frequently in the training datasets. We will going deeper into this and release more powerful solutions.

If you use this toolbox in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:

@misc{Metric3D,  author =       {Yin, Wei and Hu, Mu},  title =        {OpenMetric3D: An Open Toolbox for Monocular Depth Estimation},  howpublished = {\url{https://github.com/YvanYin/Metric3D}},  year =         {2024}}

Also please cite our papers if this help your research.

@article{hu2024metric3dv2,  title={Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation},  author={Hu, Mu and Yin, Wei and Zhang, Chi and Cai, Zhipeng and Long, Xiaoxiao and Chen, Hao and Wang, Kaixuan and Yu, Gang and Shen, Chunhua and Shen, Shaojie},  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},  year={2024},  publisher={IEEE}}

@article{yin2023metric,  title={Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image},  author={Wei Yin, Chi Zhang, Hao Chen, Zhipeng Cai, Gang Yu, Kaixuan Wang, Xiaozhi Chen, Chunhua Shen},  booktitle={ICCV},  year={2023}}

TheMetric 3D code is under a 2-clause BSD License. For further commercial inquiries, please contact Dr. Wei Yin [yvanwy@outlook.com] and Mr. Mu Hu [mhuam@connect.ust.hk].