dpt-hybrid-midas

from PIL import Image
import numpy as np
import requests
import torch

from transformers import DPTImageProcessor, DPTForDepthEstimation

image_processor = DPTImageProcessor.from_pretrained("Intel/dpt-hybrid-midas")
model = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas", low_cpu_mem_usage=True)

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

# 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,
)

# visualize the prediction
output = prediction.squeeze().cpu().numpy()
formatted = (output * 255 / np.max(output)).astype("uint8")
depth = Image.fromarray(formatted)
depth.show()

@article{DBLP:journals/corr/abs-2103-13413,
  author    = {Ren{\'{e}} Ranftl and
               Alexey Bochkovskiy and
               Vladlen Koltun},
  title     = {Vision Transformers for Dense Prediction},
  journal   = {CoRR},
  volume    = {abs/2103.13413},
  year      = {2021},
  url       = {https://arxiv.org/abs/2103.13413},
  eprinttype = {arXiv},
  eprint    = {2103.13413},
  timestamp = {Wed, 07 Apr 2021 15:31:46 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2103-13413.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}