MoGe-3
MoGe-3 is Microsoft's monocular geometry model. From one RGB image it predicts metric depth in metres, a camera-space point map, the camera intrinsics, a validity mask and surface normals. It is MoGe-2 plus a sparse 3D UNet that refines the predicted depth on a voxel grid. LibreYOLO ships the official ViT-L and ViT-g checkpoints for inference, validation and normal export.
- 작업
- depth, surface normals
- 크기
- l, g at 840 px
- 설치
pip install libreyolo- 지원 티어
- 추론 전용, v1.8.0부터 지원. 예측, 검증, 내보내기만 지원합니다. 학습 기능은 적용되지 않습니다.
- 라이선스
- 코드 MIT, 가중치 MIT. 상업적 사용
Install
MoGe-3 needs no optional extra. The sparse refiner is plain PyTorch and camera recovery uses SciPy, which is in the base install.
pip install libreyoloPredict
Weights download from the LibreYOLO Hugging Face mirrors on first use.
from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreMoGe3l-depth.pt")depth = model(SAMPLE_IMAGE).depth_map print(depth.data.shape) # (H, W) metres, inf outside the valid maskprint(depth.point_map.shape) # (H, W, 3) camera-frame points in metresprint(depth.intrinsics) # (3, 3) OpenCV pixel intrinsicsprint(depth.valid_mask.shape) # (H, W) boolfrom libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreMoGe3l-normal.pt")normal = model(SAMPLE_IMAGE).normal_mapprint(normal.array.shape) # (H, W, 3) unit vectors, OpenCV framelibreyolo predict model=LibreMoGe3l-depth.pt source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/guggenheim-bilbao.jpg save=TrueWith a -depth checkpoint, result.depth_map holds metric depth in metres
(encoding="depth", metric=True). The point map, intrinsics and validity
mask are attached to it as depth_map.point_map, depth_map.intrinsics and
depth_map.valid_mask; pixels outside the mask are inf. Points use OpenCV
axes, and the intrinsics put pixel centres at integer coordinates. With a
-normal checkpoint, result.normal_map holds unit normals in the OpenCV
camera frame.
imgsz sets the ViT token budget, (imgsz // 14) ** 2 tokens laid out to the
image aspect ratio. The default 840 is upstream's highest resolution level
(3600 tokens); 490 is close to its lowest. Inputs keep their native
resolution and every output is interpolated back to it. Inference runs in
FP32 and always applies three refinement steps, as upstream does by default.
One image runs per forward pass; there is no stacked-batch path.
CPU, CUDA and MPS all work without a compiled extension. The refiner's memory
grows with imgsz, not with the input resolution.
Variants
| Weight file | Backbone | Task |
|---|---|---|
LibreMoGe3l-depth.pt | DINOv2 ViT-L/14 | depth, point map, intrinsics, mask |
LibreMoGe3l-normal.pt | DINOv2 ViT-L/14 | normals |
LibreMoGe3g-depth.pt | DINOv2 ViT-g/14 | depth, point map, intrinsics, mask |
LibreMoGe3g-normal.pt | DINOv2 ViT-g/14 | normals |
The -depth and -normal files of one size hold the same tensors; the
suffix picks the task. Against upstream on an RTX 3090 in FP32, the
single-forward graph matches bit for bit and refined depth matches to
floating-point rounding (p99 relative difference 4.7e-6 for l, 3.7e-5 for
g).
MoGe-3 is not trainable in LibreYOLO: train() raises. Zero-shot val()
runs the shared depth and normal validators.
Export
| 작업 | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Depth | Depth to ONNX: 지원하지 않음 | Depth to TorchScript: 지원하지 않음 | Depth to ExecuTorch: 지원하지 않음 | Depth to TensorRT: 지원하지 않음 | Depth to OpenVINO: 지원하지 않음 | Depth to Paddle: 지원하지 않음 | Depth to MNN: 지원하지 않음 | Depth to RKNN: 지원하지 않음 | Depth to Axelera: 지원하지 않음 | Depth to ncnn: 지원하지 않음 | Depth to TFLite: 지원하지 않음 | Depth to CoreML: 지원하지 않음 | Depth to Core AI: 지원하지 않음 |
| Surface normals | Surface normals to ONNX: 지원함 | Surface normals to TorchScript: 지원함 | Surface normals to ExecuTorch: 지원하지 않음 | Surface normals to TensorRT: 지원하지 않음 | Surface normals to OpenVINO: 지원하지 않음 | Surface normals to Paddle: 지원하지 않음 | Surface normals to MNN: 지원하지 않음 | Surface normals to RKNN: 지원하지 않음 | Surface normals to Axelera: 지원하지 않음 | Surface normals to ncnn: 지원하지 않음 | Surface normals to TFLite: 지원하지 않음 | Surface normals to CoreML: 지원하지 않음 | Surface normals to Core AI: 지원하지 않음 |
Only the normal graph exports, to ONNX and TorchScript, on a fixed square canvas. Depth export is blocked: the refiner builds data-dependent voxel sets and camera recovery is a CPU solve.
from libreyolo import LibreYOLO # Only the normal graph exports; depth export is blocked.model = LibreYOLO("LibreMoGe3l-normal.pt")model.export(format="onnx")model.export(format="torchscript")Checkpoints
| 파일 | 입력(px) | 가중치 라이선스 |
|---|---|---|
| Depth | ||
| LibreMoGe3l-depth.pt | mit | |
| LibreMoGe3g-depth.pt | mit | |
| Surface normals | ||
| LibreMoGe3l-normal.pt | 840 | mit |
| LibreMoGe3g-normal.pt | 840 | mit |
위의 모든 파일은 현재 LibreYOLO 조직에 있으며 처음 사용할 때 내려받습니다.
Licensing
내려받는 특정 가중치의 Hugging Face 저장소에서 라이선스를 확인하십시오. LibreYOLO 조직의 모든 체크포인트에는 라이선스가 있으며 한 계열 안에서도 항상 같지는 않습니다. 해당 저장소가 신뢰할 수 있는 기준입니다. 아래 요약은 이 페이지를 마지막으로 검증했을 때 적용된 내용을 설명합니다.
관련 라이선스에 관한 설명이며 법률 자문이 아닙니다. 상업적으로 중요한 사안이라면 라이선스를 직접 읽고 별도의 법률 자문을 받으십시오.
- 원작
- MoGe-3, Microsoft
- 업스트림 라이선스
- MIT
- 업스트림 소스
- github.com/microsoft/MoGe
- LibreYOLO 코드
- MIT
- 가중치
- MIT, huggingface.co/LibreYOLO에 다시 게시됨
- 해석
- MIT is a permissive license, so the MoGe-3 code and weights can be used in commercial and closed-source products; the only obligation is to keep the copyright and license notice with copies. LibreYOLO ports the forward pass, sparse refinement and camera recovery from microsoft/MoGe at commit 74fbce054ebed49800de42d0ad0e83495065719a (MIT, Copyright Microsoft Corporation), re-expresses the FlexGEMM sparse kernels in plain PyTorch without vendoring them (FlexGEMM is MIT), and follows MIT utils3d helpers; the DINOv2 backbone keeps its separate Apache-2.0 attribution (libreyolo/models/moge3/NOTICE). The official checkpoints Ruicheng/moge-3-vitl (revision 184008f877d7ad1ad4c2cd2182a9bd1f63d0e5be) and Ruicheng/moge-3-vitg (revision 6ef26c5a4b4148dab5ccaacdb08b72dc66380475) declare MIT; LibreYOLO mirrors them unchanged, plus checkpoint metadata, as LibreYOLO/LibreMoGe3{l,g}-{depth,normal}, not gated.
MoGe-3 is by Microsoft (microsoft/MoGe).
Code and weights are MIT, so commercial use is fine. The DINOv2 backbone keeps
its Apache-2.0 attribution. LibreYOLO mirrors the official
Ruicheng/moge-3-vitl and Ruicheng/moge-3-vitg checkpoints unchanged as
LibreYOLO/LibreMoGe3{l,g}-{depth,normal}, not gated.
Citation
@misc{kong2026finedetailmonoculargeometryestimation,
title={Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement},
author={Lingyu Kong and Ruicheng Li and Ruicheng Wang and Sicheng Xu and Chengtang Yao and Jianfeng Xiang and Jiaolong Yang},
year={2026},
eprint={2607.17967},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2607.17967},
}github.com/microsoft/MoGe#-citation에 있는 저자의 인용 블록에서 복사했습니다.