This is the documentation for LibreYOLO 1.6.0. See the current version.

Install

MoGe-2 needs no optional extra. Everything it imports is in the base install.

pip install libreyolo

Predict

Weights download automatically on first use. Sizes s and l use LibreYOLO mirrors; b continues to use the upstream checkpoint.

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreMoGe2s-normal.pt")result = model(SAMPLE_IMAGE, save=True) normal = result.normal_mapprint(normal.array.shape)   # (H, W, 3) float32 unit vectors

libreyolo predict model=LibreMoGe2s-normal.pt source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/parkour.jpg save=True

MoGe-2 returns a dense field rather than a set of detections, so result.boxes is empty and conf, iou and max_det have no effect. result.normal_map holds the result: an (H, W, 3) array of unit vectors in the OpenCV camera frame, where +x is right, +y is down, +z is into the scene, and a surface facing the camera reads (0, 0, -1). Predicting a list of images runs one forward pass per image; this family has no stacked-batch fast path. See prediction for sources, streaming and result handling.

Variants

Three encoder sizes ship as separate checkpoints: ViT-S, ViT-B and ViT-L, all at the same input resolution. LibreYOLO's benchmark harness has not measured this family, so there are no published accuracy numbers to compare them by; pick a size against your own compute budget.

Validate

val() measures angular error against a paired normal-map dataset: images beside same-stem 16-bit normal PNGs, with an optional validity mask so padded and invalid pixels never count. It returns the mean and median angular error in degrees, plus the percentage of pixels within 11.25, 22.5 and 30 degrees.

from libreyolo import LibreYOLO model = LibreYOLO("LibreMoGe2s-normal.pt")metrics = model.val(data="my-dataset.yaml", imgsz=518) print(metrics["metrics/mean_angular_error"])   # degreesprint(metrics["metrics/median_angular_error"])print(metrics["metrics/within_11_25"])          # percent of pixels

libreyolo val model=LibreMoGe2s-normal.pt data=my-dataset.yaml imgsz=518

Export

Normal export uses a fixed-resolution, batch-1 runtime contract: dynamic and a batch other than 1 are rejected, and imgsz must be divisible by the ViT encoder's patch size, which LibreYOLO checks before the run starts. An exported artifact loads back through LibreYOLO() on its file suffix, so a .onnx file behaves like a checkpoint and returns the same Results.

from libreyolo import LibreYOLO model = LibreYOLO("LibreMoGe2s-normal.pt")model.export(format="onnx", imgsz=518)model.export(format="tensorrt", imgsz=518, half=True)

libreyolo export model=LibreMoGe2s-normal.pt format=onnx imgsz=518libreyolo export model=LibreMoGe2s-normal.pt format=tensorrt imgsz=518 half=True

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreMoGe2s-normal.onnx")result = model(SAMPLE_IMAGE) print(result.normal_map.array.shape)

Licensing

Citation

@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}, 
}