Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
This work presents Depth Anything, 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. 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 at https://github.com/LiheYoung/Depth-Anything.
PDF AbstractCode
Spaces
MS COCO
Cityscapes
KITTI
ADE20K
NYUv2
SUN RGB-D
BDD100K
MegaDepth
SA-1B
BlendedMVS
DIODE
DDAD
HRWSI
IRS
DIML/CVl RGB-D Dataset
Results from the Paper
Ranked #3 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Semantic Segmentation | Cityscapes test | Depth Anything | Mean IoU (class) | 84.8% | # 8 | ||
| Semantic Segmentation | Cityscapes val | Depth Anything | mIoU | 86.2 | # 7 | ||
| Monocular Depth Estimation | KITTI Eigen split | Depth Anything | absolute relative error | 0.046 | # 7 | ||
| RMSE | 1.896 | # 7 | |||||
| Sq Rel | 0.121 | # 23 | |||||
| RMSE log | 0.069 | # 6 | |||||
| Delta < 1.25 | 0.982 | # 6 | |||||
| Delta < 1.25^2 | 0.998 | # 1 | |||||
| Delta < 1.25^3 | 1.000 | # 1 | |||||
| Monocular Depth Estimation | NYU-Depth V2 | Depth Anything | RMSE | 0.206 | # 3 | ||
| absolute relative error | 0.056 | # 3 | |||||
| Delta < 1.25 | 0.984 | # 2 | |||||
| Delta < 1.25^2 | 0.998 | # 1 | |||||
| Delta < 1.25^3 | 1.000 | # 1 | |||||
| log 10 | 0.024 | # 2 |
