Depth Anything: Models, Comparisons, and How to Use It

Depth Anything is a family of open models that estimate how far every pixel is from the camera. Use V2 for sharp, detailed depth maps from a single image, and V3 when you need 3D reconstruction or camera pose from multiple images or video. Both are ready-made blocks in Roboflow Workflows, so you can add depth estimation to any vision pipeline and deploy it to images, video, or live camera streams without managing a GPU. Depth Anything is a family of depth estimation models that use visual input to estimate how far objects and surfaces are from a camera. This distance is known as depth. By estimating depth, these models help computers understand the 3D structure of a scene, supporting applications such as autonomous driving, robotics, augmented reality, and 3D scene reconstruction. The Depth Anything family has evolved through three major versions, with the latest being Depth Anything V3, released on November 14, 2025. In this guide, we'll explore Depth Anything V1, V2, and V3, highlight the key improvements in each version, compare their capabilities, and demonstrate how to build and deploy a depth estimation workflow using a Depth Anything model with Roboflow Workflows. What Is Depth Estimation? Depth estimation…