MoGe

• Original code: https://github.com/microsoft/MoGe at 74fbce0
• Code licence: MIT (permissive); files: LICENSE
• Weights licence: MIT
• Licence evidence: https://github.com/microsoft/MoGe/blob/main/README.md (License section) and the Hugging Face model cards (license: mit)
• Training data: Mixture of public synthetic and real RGB-D / multi-view datasets per the MoGe-2 and MoGe-3 papers
• Options: resolution_level = 9 (0 to 9), normals = False
• Kernel libraries: fastbb, dpt_fused, sparse_conv
• Variants: moge-2-vits-normal, moge-2-vitl-normal, moge-3-vitl
• Outputs: depth, points, intrinsics, mask, normals; kind: metric
• Input size: any H x W >= 8, resized or padded inside the model (ViT patch 14)
• Tested up to (portable, fp16, RTX 5060 Ti 16 GB): moge-2-vits-normal 3000x4000 (1.2 GiB peak allocated, 1.4 reserved); moge-2-vitl-normal 3000x4000 (2.4 GiB peak allocated, 2.5 reserved); moge-3-vitl 3000x4000 (2.6 GiB peak allocated, 3.0 reserved)
• moge-2-vits-normal 994x1482, first call: portable + torch.compile 124 s (cold Inductor cache), TensorRT fp16 131 s (ONNX + engine).
• moge-2-vits-normal load / first call: original 0.88 s / 1.501 s, portable 0.35 s / 0.084 s, kernels 0.11† s / 0.099 s
• moge-2-vitl-normal load / first call: original 7.24 s / 0.171 s, portable 1.37 s / 0.144 s, kernels 0.63† s / 0.131 s
• moge-3-vitl load / first call: original 10.6 s / 2.918 s, portable 1.02 s / 0.562 s, kernels 1.66 s / 0.301 s
• † measured in the speed sweep after the portable load (or an earlier size) in the same process: file cache and kernels are warm, so the time is lower than a fresh start.
• Protocol, moge-2-vits-normal, moge-2-vitl-normal: median of 5 after 3 warm-up, uint8 CUDA input (synthetic for bench_inputs sizes), card defaults; gc before each load; peak = max over the first call and the timed calls
• Protocol, moge-3-vitl: first call, 3 warm-up, peak reset, median of 3 rounds x median of 5

Measured

AbsRel / delta1 after a least-squares scale + shift fit (in disparity space for inverse-depth models), mean over images. Original = the original code named under Details, same checkpoint and protocol.

Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 939adfe8, 2026-11-06.

Parity

CPU, float32: max |diff| <= 0.005 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 1.5 % and p99 <= 1.5 % of the reference's median |value| (absolute error of the output depth).