模型详情：DPT-Large

Dense Prediction Transformer (DPT)模型是在140万幅图像上进行训练的，用于单目深度估计。它在Ranftl等人的论文[ Vision Transformers for Dense Prediction ]中首次提出，并在[ this repository ]中首次发布。DPT使用Vision Transformer (ViT)作为骨干，并在其上添加了一个用于单目深度估计的neck和head模块[ ]。

该模型卡片由Hugging Face团队和Intel联合编写。

如何使用

以下是在图像上进行零视差深度估计的模型使用方法：

from transformers import DPTImageProcessor, DPTForDepthEstimation
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)

processor = DPTImageProcessor.from_pretrained("Intel/dpt-large")
model = DPTForDepthEstimation.from_pretrained("Intel/dpt-large")

# prepare image for the model
inputs = 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)

更多代码示例请参考[ documentation ]。

定量分析

表1. 在单目深度估计上与现有技术的对比。我们根据[30]中定义的协议评估了跨数据集的零视差迁移。所有指标都相对于原始MiDaS模型[30]进行了计算。对于所有指标，数值越低越好。( [ Ranftl et al., 2021 ] )

BibTeX引用和引用信息

@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}
}