These are the official model checkpoints for the paper "Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation" (MDA).

📄 arXiv  |  🌐 Project page

MDA is a mixture-density depth representation that predicts several depth hypotheses (with their probabilities) at every pixel instead of forcing a single depth, which largely removes the flying-point artifacts at object boundaries that plague feed-forward depth estimators. See the Citation section to cite this work.

These two checkpoints are used for multi-view geometry prediction — spatially consistent depth and camera pose from a set of input images. They are built on two different backbones and trained with a Mixture-of-Gaussians (MoG) depth head and a logl2 objective.

Both are PyTorch Lightning checkpoints (save_weights_only=True, Lightning 2.5.6). State-dict keys are prefixed net.net.* because the network is wrapped by a Lightning module — strip the prefix and load into the bare net. These are research checkpoints and are not loadable through the standard DepthAnything3.from_pretrained HF API.

If you build on MDA, please cite: