Depth-Anything-V3

Papers using or citing this model 1

• Depth Anything 3: Recovering the Visual Space from Any Views 822 citations · 2025 · arXiv (Cornell University) · arXiv

  We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of minimal modeling, DA3 yields two key insights: a single...