Ultralytics YOLO Adds Native Depth Estimation, 7.7x Faster Than Depth Anything V2

MonaJalal_ · x · 2026-07-31

Ultralytics announced that its YOLO models now natively support monocular depth estimation. The new models predict absolute per-pixel distance in meters from a single RGB image, eliminating the need for stereo rigs or LiDAR.

With a minimum of 6.4M parameters, the model is 7.7× faster than Depth Anything V2 and runs offline, making it suitable for 3D scene reconstruction, robot navigation, and AR/VR applications.

Related event: Ultralytics YOLO Launches Native Monocular Depth Estimation(2 posts)→

Original post →

More from Models

Models channel →