Depth Anything V2

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Lihe, Kang, Bingyi, Huang, Zilong, Zhao, Zhen, Xu, Xiaogang, Feng, Jiashi, Zhao, Hengshuang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912077868695552
author Yang, Lihe
Kang, Bingyi
Huang, Zilong
Zhao, Zhen
Xu, Xiaogang
Feng, Jiashi
Zhao, Hengshuang
author_facet Yang, Lihe
Kang, Bingyi
Huang, Zilong
Zhao, Zhen
Xu, Xiaogang
Feng, Jiashi
Zhao, Hengshuang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_09414
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Depth Anything V2
Yang, Lihe
Kang, Bingyi
Huang, Zilong
Zhao, Zhen
Xu, Xiaogang
Feng, Jiashi
Zhao, Hengshuang
Computer Vision and Pattern Recognition
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.
title Depth Anything V2
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.09414