>
D
Introduction
This work presents Depth Anything V2. Without pursuing fancy techniques, we aim to reveal crucial findings to pave the way towards building a powerful monocular depth estimation model. Notably, compared with V1, this version produces much finer and more robust depth predictions through three key practices: 1) replacing all labeled real images with synthetic images, 2) scaling up the capacity of our teacher model, and 3) teaching student models via the bridge of large-scale pseudo-labeled real images. Compared with the latest models built on Stable Diffusion, our models are significantly more efficient (more than 10x faster) and more accurate. We offer models of different scales (ranging from 25M to 1.3B params) to support extensive scenarios. Benefiting from their strong generalization capability, we fine-tune them with metric depth labels to obtain our metric depth models. In addition to our models, considering the limited diversity and frequent noise in current test sets, we construct a versatile evaluation benchmark with precise annotations and diverse scenes to facilitate future research.
Training
Training Code Accessibility
Creative Commons Attribution Non Commercial 4.0
https://huggingface.co/depth-anything/Depth-Anything-V2-LargeSize Notes: "Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled image" "All images are trained at the resolution of 518×518 by resizing the shorter size to 518 followed by a random crop. When training the teacher model on synthetic images, we use a batch size of 64 for 160K iterations. In the third stage of training on pseudo-labeled real images, the model is trained with a batch size of 192 for 480K iterations. "
Parameters
Parameters
335300000Notes: 335.3M
Authors
Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao