DA3-LARGE — CoreML (.mlpackage) for monocular depth

• Input: image, RGB, 504×504, [0,1] (CoreML ImageType; ImageNet norm baked in).
• Output: depth, shape (1, 504, 504), single-channel relative depth.
• Weights: FP16. Only the backbone → depth head is converted; DA3's camera / sky / Gaussian-splat post-processing is bypassed (not needed for monocular depth).
• Conversion notes: the full DA3-LARGE backbone uses RoPE + multi-view camera tokens, so four ops were rewritten for coremltools compatibility (RoPE cartesian_prod, in-place camera-token insert, single-view empty source-token concat, and the head's meshgrid). Behaviour is unchanged for single-image input.

License & attribution