Depth Anything V2

By Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao. Neural Information Processing Systems, 2024

1,926 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/2091dcd7c80bc27ba7d1fdc0087748bb1e293e2f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. J. Liew
2. Jiaolong Yang
3. Bingyi Kang
4. Jiashi Feng
5. Donny Y. Chen
6. Sicheng Xu
7. Yu Deng
8. Ruicheng Wang

In Control and Systems Engineering

1. Bingyi Kang
2. Xin Tong
3. Jiashi Feng

Citations in the corpus

• MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision (2024, positive): “For the former, significant advancements in monocular depth estimation (MDE) have been achieved in recent years by training on large-scale data [24, 39, 60, 61, 66] or leveraging powerful pretrained models [18, 21, 27].”
• Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (2024, neutral): “Input image on top, estimated depth maps from Depth Pro, Marigold (Ke et al., 2024), Depth Anything v2 (Yang et al., 2024b), and Metric3D v2 (Hu et al., 2024) below.”
• Depth Anything 3: Recovering the Visual Space from Any Views (2025, positive): “To resolve this, we adopt a pseudo-labeling strategy inspired by prior works [112, 113].”
• Gen3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (2025, neutral): “We estimate camera parameters with DROID-SLAM [52] and predict per-frame depth using DAV2 [65].”