ZoeDepth model fine-tuned on the NYU and KITTI datasets. It was introduced in the paper
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth by Shariq et al. and first released in
this repository.
ZoeDepth extends the
DPT framework for metric (also called absolute) depth estimation, obtaining state-of-the-art results.
Disclaimer: The team releasing ZoeDepth did not write a model card for this model so this model card has been written by the Hugging Face team.
ZoeDepth adapts
DPT, a model for relative depth estimation, for so-called metric (also called absolute) depth estimation.
This means that the model is able to estimate depth in actual metric values.
You can use the raw model for tasks like zero-shot monocular depth estimation. See the
model hub to look for
other versions on a task that interests you.
The easiest is to leverage the pipeline API which abstracts away the complexity for the user:
1from transformers import pipeline
2from PIL import Image
3import requests
4
5# load pipe
6depth_estimator = pipeline(task="depth-estimation", model="Intel/zoedepth-nyu-kitti")
7
8# load image
9url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
10image = Image.open(requests.get(url, stream=True).raw)
11
12# inference
13outputs = depth_estimator(image)
14depth = outputs.depth
For more code examples, we refer to the
documentation.
1@misc{bhat2023zoedepth,
2 title={ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth},
3 author={Shariq Farooq Bhat and Reiner Birkl and Diana Wofk and Peter Wonka and Matthias Müller},
4 year={2023},
5 eprint={2302.12288},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV}
8}
