mlx-community/moge-3-vitg-mlx-fp32

MoGe-3 (VITG) — MLX

MLX port of MoGe-3: fine-detail monocular geometry estimation with self-guided sparse volumetric refinement. Predicts metric point maps, depth maps, normal maps, valid-pixel masks, and camera intrinsics from a single image.

Converted with mlx-vlm from the official model.pt checkpoint (fp32).

Usage

from mlx_vlm import load
from mlx_vlm.models.moge3.generate import MoGe3Predictor, read_image

model, processor = load("mlx-community/moge-3-vitg-mlx-fp32")
predictor = MoGe3Predictor(model, processor)
output = predictor.infer(read_image("image.jpg"), resolution_level=9)
points, depth, mask = output["points"], output["depth"], output["mask"]
normal, intrinsics = output["normal"], output["intrinsics"]

Validated against the torch reference (CPU, fp32): identical valid-pixel masks and <0.2% median relative depth error.