Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

🤖 Plain-English Summary

This work presents Depth Anything<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>While the grammatical soundness of this name may be questionable, we treat it as a whole and pay homage to Segment Anything ., a highly practical solution for robust monocular depth estimation. Further, through fine-tuning it with metric depth information from NY...

🔑 Key Findings

• Without pursuing novel technical modules, we aim to build a simple yet powerful foundation model dealing with any images under any circumstances.
• To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">~</sup>62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error.
• We investigate two simple yet effective strategies that make data scaling-up promising.

🔗 Related Resources