MoGe-2

pip install git+https://github.com/microsoft/MoGe.git

git clone https://github.com/microsoft/MoGe.git
cd MoGe
pip install -r requirements.txt   # install the requirements

import cv2
import torch
# from moge.model.v1 import MoGeModel
from moge.model.v2 import MoGeModel # Let's try MoGe-2

device = torch.device("cuda")

# Load the model from huggingface hub (or load from local).
model = MoGeModel.from_pretrained("Ruicheng/moge-2-vitl-normal").to(device)                             

# Read the input image and convert to tensor (3, H, W) with RGB values normalized to [0, 1]
input_image = cv2.cvtColor(cv2.imread("PATH_TO_IMAGE.jpg"), cv2.COLOR_BGR2RGB)                       
input_image = torch.tensor(input_image / 255, dtype=torch.float32, device=device).permute(2, 0, 1)    

# Infer 
output = model.infer(input_image)
"""
`output` has keys "points", "depth", "mask", "normal" (optional) and "intrinsics",
The maps are in the same size as the input image. 
{
    "points": (H, W, 3),    # point map in OpenCV camera coordinate system (x right, y down, z forward). For MoGe-2, the point map is in metric scale.
    "depth": (H, W),        # depth map
    "normal": (H, W, 3)     # normal map in OpenCV camera coordinate system. (available for MoGe-2-normal)
    "mask": (H, W),         # a binary mask for valid pixels. 
    "intrinsics": (3, 3),   # normalized camera intrinsics
}
"""

# Using the command line tool
moge app        # will run MoGe-2 demo by default.

# In this repo
python moge/scripts/app.py   # --share for Gradio public sharing

# Save the output [maps], [glb] and [ply] files
moge infer -i IMAGES_FOLDER_OR_IMAGE_PATH --o OUTPUT_FOLDER --maps --glb --ply

# Show the result in a window (requires pyglet < 2.0, e.g. pip install pyglet==1.5.29)
moge infer -i IMAGES_FOLDER_OR_IMAGE_PATH --o OUTPUT_FOLDER --show

Usage: moge infer [OPTIONS]

  Inference script

Options:
  -i, --input PATH            Input image or folder path. "jpg" and "png" are
                              supported.
  --fov_x FLOAT               If camera parameters are known, set the
                              horizontal field of view in degrees. Otherwise,
                              MoGe will estimate it.
  -o, --output PATH           Output folder path
  --pretrained TEXT           Pretrained model name or path. If not provided,
                              the corresponding default model will be chosen.
  --version [v1|v2]           Model version. Defaults to "v2"
  --device TEXT               Device name (e.g. "cuda", "cuda:0", "cpu").
                              Defaults to "cuda"
  --fp16                      Use fp16 precision for much faster inference.
  --resize INTEGER            Resize the image(s) & output maps to a specific
                              size. Defaults to None (no resizing).
  --resolution_level INTEGER  An integer [0-9] for the resolution level for
                              inference. Higher value means more tokens and
                              the finer details will be captured, but
                              inference can be slower. Defaults to 9. Note
                              that it is irrelevant to the output size, which
                              is always the same as the input size.
                              `resolution_level` actually controls
                              `num_tokens`. See `num_tokens` for more details.
  --num_tokens INTEGER        number of tokens used for inference. A integer
                              in the (suggested) range of `[1200, 2500]`.
                              `resolution_level` will be ignored if
                              `num_tokens` is provided. Default: None
  --threshold FLOAT           Threshold for removing edges. Defaults to 0.01.
                              Smaller value removes more edges. "inf" means no
                              thresholding.
  --maps                      Whether to save the output maps (image, point
                              map, depth map, normal map, mask) and fov.
  --glb                       Whether to save the output as a.glb file. The
                              color will be saved as a texture.
  --ply                       Whether to save the output as a.ply file. The
                              color will be saved as vertex colors.
  --show                      Whether show the output in a window. Note that
                              this requires pyglet<2 installed as required by
                              trimesh.
  --help                      Show this message and exit.

@inproceedings{wang2025moge,
  title={Moge: Unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision},
  author={Wang, Ruicheng and Xu, Sicheng and Dai, Cassie and Xiang, Jianfeng and Deng, Yu and Tong, Xin and Yang, Jiaolong},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={5261--5271},
  year={2025}
}

@misc{wang2025moge2,
      title={MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details}, 
      author={Ruicheng Wang and Sicheng Xu and Yue Dong and Yu Deng and Jianfeng Xiang and Zelong Lv and Guangzhong Sun and Xin Tong and Jiaolong Yang},
      year={2025},
      eprint={2507.02546},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.02546}, 
}