🚀 具有DINOv2主干的DPT模型
本项目基于DPT(Dense Prediction Transformer)模型,采用DINOv2作为主干网络,能够实现强大的深度估计功能。该模型的提出参考了相关研究论文,为视觉领域的深度估计任务提供了有效的解决方案。
🚀 快速开始
模型详情
DPT(密集预测变换器)模型采用DINOv2作为主干网络,此模型由Oquab等人在论文 DINOv2: Learning Robust Visual Features without Supervision 中提出。

DPT架构。取自 原论文。
资源链接
使用Transformers库调用模型
from transformers import AutoImageProcessor, 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)
image_processor = AutoImageProcessor.from_pretrained("facebook/dpt-dinov2-base-kitti")
model = DPTForDepthEstimation.from_pretrained("facebook/dpt-dinov2-base-kitti")
inputs = image_processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
predicted_depth = outputs.predicted_depth
prediction = torch.nn.functional.interpolate(
predicted_depth.unsqueeze(1),
size=image.size[::-1],
mode="bicubic",
align_corners=False,
)
output = prediction.squeeze().cpu().numpy()
formatted = (output * 255 / np.max(output)).astype("uint8")
depth = Image.fromarray(formatted)
📚 模型使用
预期用途
该模型旨在展示使用DPT框架并以DINOv2作为主干网络可以得到一个强大的深度估计器。
BibTeX引用信息
@misc{oquab2023dinov2,
title={DINOv2: Learning Robust Visual Features without Supervision},
author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
year={2023},
eprint={2304.07193},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
📄 许可证
本项目采用Apache-2.0许可证。