Translation: The new MDE model, Depth Anything, launched by the University of Hong Kong in collaboration with TikTok, enables monocular depth estimation using large-scale unlabeled images. This model boasts robust performance and practicality, along with enhanced zero-shot capabilities. By designing a data engine to collect and automatically label large-scale unlabeled data, the model expands dataset size and reduces generalization errors. Its emergence brings new hope to fields such as robotics, autonomous driving, and virtual reality.