Paper summary
Paper summary: Depth Anything V2
Depth Anything V2 trains a monocular depth teacher on synthetic images only, then teaches student models through large-scale pseudo-labelled real images, giving finer and more robust depth than V1.
- Swapping all labelled real images for synthetic ones avoids the noisy depth labels of real datasets.
- Pseudo-labelled real images bridge the gap between synthetic training and the real world.