Official PyTorch implementation of Metric3Dv1 and Metric3Dv2:
[1] Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
[2] Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation
-
Droid slam codes
-
Release the ViT-giant2 model
-
Focal length free mode
-
Floating noise removing mode
-
Improving HuggingFace Demo and Visualization
-
[2024/4/11]
Training codes are released! -
[2024/3/18]
HuggingFace GPU version updated! -
[2024/3/18]
Project page released! -
[2024/3/18]
Metric3D V2 models released, supporting metric depth and surface normal now! -
[2023/8/10]
Inference codes, pre-trained weights, and demo released. -
[2023/7]
Metric3D accepted by ICCV 2023! -
[2023/4]
The Champion of 2nd Monocular Depth Estimation Challenge in CVPR 2023
Metric3D is a versatile geometric foundation model for high-quality and zero-shot metric depth and surface normal estimation from a single image. It excels at solving in-the-wild scene reconstruction.
Our models rank 1st on the routing KITTI and NYU benchmarks.
Backbone | KITTI Ξ΄1 β | KITTI Ξ΄2 β | KITTI AbsRel β | KITTI RMSE β | KITTI RMS_log β | NYU Ξ΄1 β | NYU Ξ΄2 β | NYU AbsRel β | NYU RMSE β | NYU log10 β | |
---|---|---|---|---|---|---|---|---|---|---|---|
ZoeDepth | ViT-Large | 0.971 | 0.995 | 0.053 | 2.281 | 0.082 | 0.953 | 0.995 | 0.077 | 0.277 | 0.033 |
ZeroDepth | ResNet-18 | 0.968 | 0.996 | 0.057 | 2.087 | 0.083 | 0.954 | 0.995 | 0.074 | 0.269 | 0.103 |
IEBins | SwinT-Large | 0.978 | 0.998 | 0.050 | 2.011 | 0.075 | 0.936 | 0.992 | 0.087 | 0.314 | 0.031 |
DepthAnything | ViT-Large | 0.982 | 0.998 | 0.046 | 1.985 | 0.069 | 0.984 | 0.998 | 0.056 | 0.206 | 0.024 |
Ours | ViT-Large | 0.985 | 0.998 | 0.999 | 1.985 | 0.064 | 0.989 | 0.998 | 0.047 | 0.183 | 0.020 |
Ours | ViT-giant2 | 0.989 | 0.998 | 1.000 | 1.766 | 0.060 | 0.987 | 0.997 | 0.045 | 0.187 | 0.015 |
Even compared to recent affine-invariant depth methods (Marigold and Depth Anything), our metric-depth (and normal) models still show superior performance.
#Data for Pretrain and Train | KITTI Absrel β | KITTI Ξ΄1 β | NYUv2 AbsRel β | NYUv2 Ξ΄1 β | DIODE-Full AbsRel β | DIODE-Full Ξ΄1 β | Eth3d AbsRel β | Eth3d Ξ΄1 β | |
---|---|---|---|---|---|---|---|---|---|
OmniData (v2, ViT-L) | 1.3M + 12.2M | 0.069 | 0.948 | 0.074 | 0.945 | 0.149 | 0.835 | 0.166 | 0.778 |
MariGold (LDMv2) | 5B + 74K | 0.099 | 0.916 | 0.055 | 0.961 | 0.308 | 0.773 | 0.127 | 0.960 |
DepthAnything (ViT-L) | 142M + 63M | 0.076 | 0.947 | 0.043 | 0.981 | 0.277 | 0.759 | 0.065 | 0.882 |
Ours (ViT-L) | 142M + 16M | 0.042 | 0.979 | 0.042 | 0.980 | 0.141 | 0.882 | 0.042 | 0.987 |
Ours (ViT-g) | 142M + 16M | 0.043 | 0.982 | 0.043 | 0.981 | 0.136 | 0.895 | 0.042 | 0.983 |
Our models also show powerful performance on normal benchmarks.
NYU 11.25Β° β | NYU Mean β | NYU RMS β | ScanNet 11.25Β° β | ScanNet Mean β | ScanNet RMS β | iBims 11.25Β° β | iBims Mean β | iBims RMS β | |
---|---|---|---|---|---|---|---|---|---|
EESNU | 0.597 | 16.0 | 24.7 | 0.711 | 11.8 | 20.3 | 0.585 | 20.0 | - |
IronDepth | - | - | - | - | - | - | 0.431 | 25.3 | 37.4 |
PolyMax | 0.656 | 13.1 | 20.4 | - | - | - | - | - | - |
Ours (ViT-L) | 0.688 | 12.0 | 19.2 | 0.760 | 9.9 | 16.4 | 0.694 | 19.4 | 34.9 |
Ours (ViT-g) | 0.662 | 13.2 | 20.2 | 0.778 | 9.2 | 15.3 | 0.697 | 19.6 | 35.2 |
For the ViT models, use the following environmentοΌ
pip install -r requirements_v2.txt
For ConvNeXt-L, it is
pip install -r requirements_v1.txt
With off-the-shelf depth datasets, we need to generate json annotaions in compatible with this dataset, which is organized by:
dict(
'files':list(
dict(
'rgb': 'data/kitti_demo/rgb/xxx.png',
'depth': 'data/kitti_demo/depth/xxx.png',
'depth_scale': 1000.0 # the depth scale of gt depth img.
'cam_in': [fx, fy, cx, cy],
),
dict(
...
),
...
)
)
To generate such annotations, please refer to the "Inference" section.
In mono/configs
we provide different config setups.
Intrinsics of the canonical camera is set bellow:
canonical_space = dict(
img_size=(512, 960),
focal_length=1000.0,
),
where cx and cy is set to be half of the image size.
Inference settings are defined as
depth_range=(0, 1),
depth_normalize=(0.3, 150),
crop_size = (512, 1088),
where the images will be first resized as the crop_size
and then fed into the model.
Please refer to training/README.md
Encoder | Decoder | Link | |
---|---|---|---|
v1-T | ConvNeXt-Tiny | Hourglass-Decoder | Coming soon |
v1-L | ConvNeXt-Large | Hourglass-Decoder | Download |
v2-S | DINO2reg-ViT-Small | RAFT-4iter | Download |
v2-L | DINO2reg-ViT-Large | RAFT-8iter | Download |
v2-g | DINO2reg-ViT-giant2 | RAFT-8iter | Coming soon |
- put the trained ckpt file
model.pth
inweight/
. - generate data annotation by following the code
data/gene_annos_kitti_demo.py
, which includes 'rgb', (optional) 'intrinsic', (optional) 'depth', (optional) 'depth_scale'. - change the 'test_data_path' in
test_*.sh
to the*.json
path. - run
source test_kitti.sh
orsource test_nyu.sh
.
- put the trained ckpt file
model.pth
inweight/
. - change the 'test_data_path' in
test.sh
to the image folder path. - run
source test_vit.sh
for transformers andsource test.sh
for convnets. As no intrinsics are provided, we provided by default 9 settings of focal length.
Because the focal length is not properly set! Please find a proper focal length by modifying codes here yourself.
Because the images are too large! Use smaller ones instead.
First be sure all black padding regions at image boundaries are cropped out. Then please try again. Besides, metric 3D is not almighty. Some objects (chandeliers, drones...) / camera views (aerial view, bev...) do not occur frequently in the training datasets. We will going deeper into this and release more powerful solutions.
@article{hu2024metric3dv2,
title={A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation},
author={Hu, Mu and Yin, Wei, and Zhang, Chi and Cai, Zhipeng and Long, Xiaoxiao and Chen, Hao, and Wang, Kaixuan and Yu, Gang and Shen, Chunhua and Shen, Shaojie},
booktitle={arXiv},
year={2024}
}
@article{yin2023metric,
title={Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image},
author={Wei Yin, Chi Zhang, Hao Chen, Zhipeng Cai, Gang Yu, Kaixuan Wang, Xiaozhi Chen, Chunhua Shen},
booktitle={ICCV},
year={2023}
}
The Metric 3D code is under a 2-clause BSD License for non-commercial usage. For further questions, contact Dr. yvan.yin [[email protected]] and Mr. mu.hu [[email protected]].