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.
- Task
- depth, surface normals
- Dimensioni
- l, g at 840 px
- Installa
pip install libreyolo- Livello di supporto
- Solo inferenza, dalla v1.8.0. Solo predizione, validazione ed esportazione. Le funzionalità di addestramento non si applicano.
- Licenze
- Codice MIT, pesi MIT. Uso commerciale
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
| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Depth | Depth to ONNX: non supportato | Depth to TorchScript: non supportato | Depth to ExecuTorch: non supportato | Depth to TensorRT: non supportato | Depth to OpenVINO: non supportato | Depth to Paddle: non supportato | Depth to MNN: non supportato | Depth to RKNN: non supportato | Depth to Axelera: non supportato | Depth to ncnn: non supportato | Depth to TFLite: non supportato | Depth to CoreML: non supportato | Depth to Core AI: non supportato |
| Surface normals | Surface normals to ONNX: supportato | Surface normals to TorchScript: supportato | Surface normals to ExecuTorch: non supportato | Surface normals to TensorRT: non supportato | Surface normals to OpenVINO: non supportato | Surface normals to Paddle: non supportato | Surface normals to MNN: non supportato | Surface normals to RKNN: non supportato | Surface normals to Axelera: non supportato | Surface normals to ncnn: non supportato | Surface normals to TFLite: non supportato | Surface normals to CoreML: non supportato | Surface normals to Core AI: non supportato |
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
| File | Ingresso (px) | Licenza dei pesi |
|---|---|---|
| Depth | ||
| LibreMoGe3l-depth.pt | mit | |
| LibreMoGe3g-depth.pt | mit | |
| Surface normals | ||
| LibreMoGe3l-normal.pt | 840 | mit |
| LibreMoGe3g-normal.pt | 840 | mit |
Oggi tutti i file elencati sopra sono presenti nell<link>organizzazione LibreYOLO</link> e vengono scaricati al primo utilizzo.
Licensing
Controlla la licenza nel repository Hugging Face degli specifici pesi che scarichi. Ogni checkpoint nell<link>organizzazione LibreYOLO</link> ne include una e non è sempre la stessa per tutta la famiglia. Quel repository è la fonte autorevole; il riepilogo seguente descrive le condizioni applicabili al momento dellultima verifica di questa pagina.
Questa è una descrizione delle licenze coinvolte, non una consulenza legale. Se la risposta è importante a fini commerciali, leggi personalmente le licenze e chiedi una consulenza indipendente.
- Lavoro originale
- MoGe-3, Microsoft
- Licenza upstream
- MIT
- Sorgente upstream
- github.com/microsoft/MoGe
- Codice LibreYOLO
- MIT
- Pesi
- MIT, ripubblicati su huggingface.co/LibreYOLO
- Interpretazione
- 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},
}Copiato dal blocco di citazione degli autori disponibile su github.com/microsoft/MoGe#-citation.