🚀 带有DINOv2主干的DPT模型
本模型结合了DPT(Dense Prediction Transformer)架构与DINOv2主干,能够有效进行深度估计,为视觉领域的相关任务提供了强大的支持。
🚀 快速开始
模型详情
DPT(Dense Prediction Transformer)模型采用了DINOv2作为主干,该架构由Oquab等人在论文 DINOv2: Learning Robust Visual Features without Supervision 中提出。

DPT架构。取自 原论文。
参考资源
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-nyu")
model = DPTForDepthEstimation.from_pretrained("facebook/dpt-dinov2-base-nyu")
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)
📚 详细文档
模型用途
预期用途
该模型旨在展示使用DPT框架并以DINOv2作为主干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。