Multiview models

5 multiview models. Each section says what the model is, whether it may be used commercially and how fast it is; licences and checks are under Details.

Input: several images of one scene (posed and calibrated for multi-view stereo, unposed otherwise). Output: depth maps and, where the model predicts them, cameras and 3-D points.

Measured on RTX 5060 Ti, torch 2.14.1+cu130; fastforks bench MODEL --size HxW measures yours. The summary uses each model's own benchmark input (see Benchmarks): kernels time with its speed-up over the faster original run, and kernels peak reserved memory with its ratio to the smaller original one. Where measured (one variant per family), a variant's table also lists portable under torch.compile and the fp16 TensorRT engine of portable (export; memory: the engine's device memory). – = not measured.

Other devices: Apple M1 Pro 16 GB, NVIDIA L4, NVIDIA L40S, NVIDIA A10, NVIDIA A100-SXM4-40GB, NVIDIA RTX PRO 6000; across devices.

All models

Modes, licences, training data and outputs per model

Commercial status per variant: yes if the code and the weights licence both allow commercial use (the training data is listed but does not change it; weights without a licence of their own are assumed to carry the code licence); no if either forbids it; unclear for custom licence terms (treat as no).

model	modes	code licence	weights licence	training data	commercial	outputs
mapanything-apache	portable, kernels	Apache-2.0	Apache-2.0	unstated	yes	depth, confidence, mask, world_points, intrinsics, cam_to_world, metric_scale
mvsanywhere	portable, kernels	LicenseRef-noncommercial AND CC-BY-NC-SA-4.0	LicenseRef-noncommercial AND CC-BY-NC-SA-4.0 (assumed from code)	unstated	no (code: LicenseRef-noncommercial AND CC-BY-NC-SA-4.0 (noncommercial); weights: LicenseRef-noncommercial AND CC-BY-NC-SA-4.0 (assumed from code))	depth, mask, sky, depth_range
patchmatchnet	portable, kernels	MIT	MIT (assumed from code)	dtu	yes	depth, confidence
vggt-1b	portable, kernels	LicenseRef-VGGT	CC-BY-NC-4.0	unstated	no (weights: CC-BY-NC-4.0)	depth, confidence, world_points, intrinsics, cam_to_world, points_confidence
vggt-omega-1b-512	portable, kernels	LicenseRef-FAIR-Noncommercial-Research	LicenseRef-FAIR-Noncommercial-Research	unstated	no (code: LicenseRef-FAIR-Noncommercial-Research (noncommercial); weights: LicenseRef-FAIR-Noncommercial-Research)	depth, confidence, intrinsics, cam_to_world

Training datasets