Models / meta / DPT DINOv2 Large KITTI

DPT DINOv2 Large KITTI

metavision

A monocular depth estimation model based on DINOv2 large backbone, fine-tuned on the KITTI dataset.

imagevision

Specs

Context & limits

—

context window

—

max output

Lifecycle

Dates

released2023-10-01

Resources

homepagehttps://huggingface.co/facebook/dpt-dinov2-large-kitti ↗