Depth Anything V2 Metric Indoor Base Hf

🚀 Depth Anything V2 (Fine-tuned for Metric Depth Estimation) - Transformers Version

This model is a fine - tuned variant of Depth Anything V2 for indoor metric depth estimation, utilizing the synthetic Hypersim datasets. It's compatible with the transformers library.

Depth Anything V2, introduced in the paper of the same name by Lihe Yang et al., shares the architecture of the original Depth Anything. It uses synthetic data and a larger - capacity teacher model to achieve more refined and robust depth predictions. This fine - tuned version for metric depth estimation was first released in this repository.

✨ Features

• Multiple Metric Depth Models: Six metric depth models of three scales are available for indoor and outdoor scenes respectively. | Base Model | Params | Indoor (Hypersim) | Outdoor (Virtual KITTI 2) | |----------|---------|---------|---------| | Depth - Anything - V2 - Small | 24.8M | Model Card | Model Card | | Depth - Anything - V2 - Base | 97.5M | Model Card | Model Card | | Depth - Anything - V2 - Large | 335.3M | Model Card | Model Card |

📚 Documentation

Model description

Depth Anything V2 uses the DPT architecture with a DINOv2 backbone. It's trained on ~600K synthetic labeled images and ~62 million real unlabeled images, achieving state - of - the - art results in both relative and absolute depth estimation.

Depth Anything overview. Taken from the original paper.

Intended uses & limitations

You can use the raw model for zero - shot depth estimation. Check the model hub for other versions related to your task.

📦 Installation

• Using pip with a specific version: transformers>=4.45.0
• Installing the latest version from source:

pip install git+https://github.com/huggingface/transformers

💻 Usage Examples

Basic Usage

Here is how to use this model to perform zero - shot depth estimation:

from transformers import pipeline
from PIL import Image
import requests

# load pipe
pipe = pipeline(task="depth-estimation", model="depth-anything/Depth-Anything-V2-Metric-Indoor-Base-hf")

# load image
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

# inference
depth = pipe(image)["depth"]

Advanced Usage

Alternatively, you can use the model and processor classes:

from transformers import AutoImageProcessor, AutoModelForDepthEstimation
import torch
import numpy as np
from PIL import Image
import requests

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

image_processor = AutoImageProcessor.from_pretrained("depth-anything/Depth-Anything-V2-Metric-Indoor-Base-hf")
model = AutoModelForDepthEstimation.from_pretrained("depth-anything/Depth-Anything-V2-Metric-Indoor-Base-hf")

# prepare image for the model
inputs = image_processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)
    predicted_depth = outputs.predicted_depth

# interpolate to original size
prediction = torch.nn.functional.interpolate(
    predicted_depth.unsqueeze(1),
    size=image.size[::-1],
    mode="bicubic",
    align_corners=False,
)

For more code examples, please refer to the documentation.

📄 License

Citation

@article{depth_anything_v2,
  title={Depth Anything V2},
  author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
  journal={arXiv:2406.09414},
  year={2024}
}

@inproceedings{depth_anything_v1,
  title={Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data}, 
  author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2024}
}