Dpt Dinov2 Small Nyu

🚀 模型卡片：基于DINOv2主干的DPT模型

本模型使用DINOv2作为主干的DPT（密集预测变换器）模型，由Oquab等人在论文 DINOv2: Learning Robust Visual Features without Supervision 中提出。该模型可用于强大的深度估计任务。

📚 详细文档

模型详情

DPT（Dense Prediction Transformer）模型采用DINOv2作为主干，该模型由Oquab等人在 DINOv2: Learning Robust Visual Features without Supervision 中提出。

DPT架构。取自 原论文。

参考资源

• DINOv2论文
• DPT论文

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-small-nyu")
model = DPTForDepthEstimation.from_pretrained("facebook/dpt-dinov2-small-nyu")

# 为模型准备图像
inputs = image_processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)
    predicted_depth = outputs.predicted_depth

# 插值到原始大小
prediction = torch.nn.functional.interpolate(
    predicted_depth.unsqueeze(1),
    size=image.size[::-1],
    mode="bicubic",
    align_corners=False,
)

# 可视化预测结果
output = prediction.squeeze().cpu().numpy()
formatted = (output * 255 / np.max(output)).astype("uint8")
depth = Image.fromarray(formatted)

💻 使用示例

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

本模型采用Apache-2.0许可证。