Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

By Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao. Computer Vision and Pattern Recognition, 2024

1,978 citations recorded by the source corpus.

This work presents Depth Anything11While the grammatical soundness of this name may be questionable, we treat it as a whole and pay homage to Segment Anything [26]., a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerful foundation model dealing with any images under any circumstances. To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error. We investigate two simple yet effective strategies that make data scaling-up promising. First, a more challenging optimization target is created by leveraging data augmentation tools. It compels the model to actively seek extra visual knowledge and acquire robust representations. Second, an auxiliary supervision is developed to enforce the model to inherit rich semantic priors from pre-trained encoders. We evaluate its zero-shot capabilities extensively, including six public datasets and randomly captured photos. It demonstrates impressive generalization ability (Figure 1). Further, through fine-tuning it with metric depth information from NYUv2 and KITTI, new SOTAs are set. Our better depth model also results in a better depth-conditioned ControlNet. Our models are released here.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/afea54c7f17f4fac0f71bebed6bc782ed69d8bd0

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Management Science and Operations Research

Citations in the corpus

Continuous 3D Perception Model with Persistent State (2025, neutral): “Extensive research [7, 27, 42, 55, 58, 59, 85, 92] focuses on estimating monocular depth.”
SpatialRGPT: Grounded Spatial Reasoning in Vision Language Model (2024, methodology): “The lower rows report on quantitative QAs, detailing their success rate (answers within ± 25 % of the ground truth value) and the absolute relative error [40, 39].”
Gen3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (2025, positive): “Recently, depth estimation has achieved significant progress across various domains [20, 24, 56, 64, 65], such as indoor, outdoor, or self-driving scenes.”
VGGT: Visual Geometry Grounded Transformer (2025, neutral): “There are several recent examples of large 3D neural networks, including DepthAnything [97], MoGe [86], and LRM [34].”
GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image (2024, methodology): “However, the generated images conditioned on depth map of DepthAnything [68] and normal map of DSINE [3] fail to keep similar 3D structures with the input image.”
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models (2024, background): “…of SoM [55]. nx.draw(G, pos, with_labels=True) This module takes an image as input and returns a depth map. y_I = points["I"][1] x_X = x_I + 100 Depth estimation. y_X = y_I + slope_bd * (x_X - x_I) # Plot the auxiliary line IX in red color The underlying model is DepthAnything [56]. node 4.”
FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting (2023, neutral): “4, we ablate our design choices on the the LLFF dataset under the 3-view setting.”
Depth Anything V2 (2024, positive): “One group [7, 6, 89, 28] is based on discriminative models, e . g ., BEiT [4] and DINOv2 [50], while the other [31, 20, 25] is based on generative models, e . g ., Stable Diffusion (SD) [59].”
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (2024, neutral): “Our baselines include Depth Anything (Yang et al., 2024a), Metric3D (Yin et al., 2023), PatchFusion (Li et al., 2024a), UniDepth (Piccinelli et al., 2024), ZeroDepth (Guizilini et al., 2023) and ZoeDepth (Bhat et al., 2023).”
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].”
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (2024, background): “Recent deep learning works (Ranftl et al., 2020; 2021; Saxena et al., 2024; Ke et al., 2024) target zero-shot performance and with large-scale training combined with synthetic datasets (Yang et al., 2024a;b) show strong generalization to diverse domains.”