Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Paper
•
2401.10891
•
Published
•
59
Depth Anything models, foundation models for monocular depth estimation, trained on 1.5 million labeled images and 62 million unlabeled images
Note This model gives the highest quality, but is also the most heavy in terms of computation.
Note The most efficient model, with promising performance
Note This model gives the highest quality, but is also the most heavy in terms of computation.
Note The most efficient model, with promising performance