# MoGe **Repository Path**: minttang/MoGe ## Basic Information - **Project Name**: MoGe - **Description**: No description available - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2025-07-10 - **Last Updated**: 2025-07-10 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # MoGe: Accurate Monocular Geometry Estimation MoGe is a powerful model for recovering 3D geometry from monocular open-domain images, including metric point maps, metric depth maps, normal maps and camera FOV. ***Check our websites ([MoGe-1](https://wangrc.site/MoGePage), [MoGe-2](https://wangrc.site/MoGe2Page)) for videos and interactive results!*** ## ๐Ÿ“– Publications ### MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
arXiv Project Page https://github.com/user-attachments/assets/8f9ae680-659d-4f7f-82e2-b9ed9d6b988a
### MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
arXiv Project Page
Method overview ## ๐ŸŒŸ Features * **Accurate 3D geometry estimation**: Estimate point maps & depth maps & [normal maps](docs/normal.md) from open-domain single images with high precision -- all capabilities in one model, one forward pass. * **Optional ground-truth FOV input**: Enhance model accuracy further by providing the true field of view. * **Flexible resolution support**: Works seamlessly with various resolutions and aspect ratios, from 2:1 to 1:2. * **Optimized for speed**: Achieves 60ms latency per image (A100 or RTX3090, FP16, ViT-L). Adjustable inference resolution for even faster speed. ## โœจ News ***(2025-06-10)*** * โ—**Released MoGe-2**, a state-of-the-art model for monocular geometry, with these new capabilities in one unified model: * point map prediction in **metric scale**; * comparable and even better performance over MoGe-1; * significant improvement of **visual sharpness**; * high-quality [**normal map** estimation](docs/normal.md); * lower inference latency. ## ๐Ÿ“ฆ Installation ### Install via pip ```bash pip install git+https://github.com/microsoft/MoGe.git ``` ### Or clone this repository ```bash git clone https://github.com/microsoft/MoGe.git cd MoGe pip install -r requirements.txt # install the requirements ``` Note: MoGe should be compatible with most requirements versions. Please check the `requirements.txt` for more details if you encounter any dependency issues. ## ๐Ÿค— Pretrained Models Our pretrained models are available on the huggingface hub:
Version Hugging Face Model Metric scale Normal #Params
MoGe-1 Ruicheng/moge-vitl - - 314M
MoGe-2 Ruicheng/moge-2-vitl โœ… - 326M
Ruicheng/moge-2-vitl-normal โœ… โœ… 331M
Ruicheng/moge-2-vitb-normal โœ… โœ… 104M
Ruicheng/moge-2-vits-normal โœ… โœ… 35M
> NOTE: `moge-2-vitl-normal` has full capabilities, with almost the same level of performance as `moge-2-vitl` plus extra normal map estimation. You may import the `MoGeModel` class of the matched version, then load the pretrained weights via `MoGeModel.from_pretrained("HUGGING_FACE_MODEL_REPO_NAME")` with automatic downloading. If loading a local checkpoint, replace the model name with the local path. ## ๐Ÿ’ก Minimal Code Example Here is a minimal example for loading the model and inferring on a single image. ```python 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 } """ ``` For more usage details, see the `MoGeModel.infer()` docstring. ## ๐Ÿ’ก Usage ### Gradio demo | `moge app` > The demo for MoGe-1 is also available at our [Hugging Face Space](https://huggingface.co/spaces/Ruicheng/MoGe). ```bash # 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 ``` See also [`moge/scripts/app.py`](moge/scripts/app.py) ### Inference | `moge infer` Run the script `moge/scripts/infer.py` via the following command: ```bash # 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 ``` For detailed options, run `moge infer --help`: ``` 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. ``` See also [`moge/scripts/infer.py`](moge/scripts/infer.py) ### 360ยฐ panorama images | `moge infer_panorama` > *NOTE: This is an experimental extension of MoGe.* The script will split the 360-degree panorama image into multiple perspective views and infer on each view separately. The output maps will be combined to produce a panorama depth map and point map. Note that the panorama image must have spherical parameterization (e.g., environment maps or equirectangular images). Other formats must be converted to spherical format before using this script. Run `moge infer_panorama --help` for detailed options.
The photo is from [this URL](https://commons.wikimedia.org/wiki/Category:360%C2%B0_panoramas_with_equirectangular_projection#/media/File:Braunschweig_Sankt-%C3%84gidien_Panorama_02.jpg)
See also [`moge/scripts/infer_panorama.py`](moge/scripts/infer_panorama.py) ## ๐Ÿ‹๏ธโ€โ™‚๏ธ Training & Finetuning See [docs/train.md](docs/train.md) ## ๐Ÿงช Evaluation See [docs/eval.md](docs/eval.md) ## โš–๏ธ License MoGe code is released under the MIT license, except for DINOv2 code in `moge/model/dinov2` which is released by Meta AI under the Apache 2.0 license. See [LICENSE](LICENSE) for more details. ## ๐Ÿ“œ Citation If you find our work useful in your research, we gratefully request that you consider citing our paper: ``` @misc{wang2024moge, 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}, year={2024}, eprint={2410.19115}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2410.19115}, } @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}, } ```