The one depth estimation model in our catalog.
1 model · 1 open-weight · prices synced Sep 12, 2026
Depth models predict distance per pixel, and the deciding question is whether you need relative depth (what is nearer) or metric depth (how far, in units), because those are different problems.
Monocular models in the MiDaS and Depth Anything lineage generalize across scene types and produce excellent relative depth maps: correct ordering and clean boundaries. That is enough for background blur, AR occlusion, image editing, and scene understanding, and it works with any ordinary camera.
Real distances require metric depth models (trained for absolute scale, often per-domain), stereo cameras, or depth sensors. Monocular metric estimates carry real error that varies by scene, so navigation, measurement, and safety systems should verify against ground truth in their own environment before trusting any model output.
The bottom line: For ordering and visual effects, a monocular relative-depth model is enough. For real distances, use a metric model validated in your environment, or add stereo or a sensor.
Depth estimation is the task of predicting how far each pixel in an image is from the camera, turning a flat photo into a 2.5D understanding of the scene. Monocular models infer depth from a single image using learned priors and may output relative depth (ordering) or metric depth (real distances); stereo and multi-view methods compute it geometrically from parallax. Models in the MiDaS and Depth Anything lineage train across many datasets to generalize broadly, and accuracy is measured by error against sensor ground truth. Depth enables robot and drone navigation, AR occlusion that looks correct, portrait background blur, and scene layout analysis without special hardware. This page covers the one depth estimation model we track, Depth Anything V2, open-weight and free to self-host.
Depth Anything V2 is the only depth estimation model in our catalog, so there is nothing here to rank it against. For fixed categories in production, a model fine-tuned on your own data typically beats any general-purpose model. Try it on your own images to see whether it fits.
Yes. The one depth estimation model we track, Depth Anything V2, is open-weight, free to self-host under its license (Apache 2.0).
This page lists the one depth estimation models in the Roboflow Playground catalog, all of them open-weight and free to self-host. Compare licenses, parameters, and release dates side by side, or open any model page for full details.