Dpt Dinov2 Large Kitti

🚀 模型卡片：基於DINOv2主幹的DPT模型

本模型使用DPT（密集預測變換器）架構，並以DINOv2作為主幹網絡，可用於強大的深度估計任務。它基於Oquab等人發表的論文 DINOv2: Learning Robust Visual Features without Supervision 開發。

📚 詳細文檔

模型詳情

DPT（Dense Prediction Transformer）模型採用DINOv2作為主幹網絡，該模型由Oquab等人在 DINOv2: Learning Robust Visual Features without Supervision 中提出。

DPT架構。取自 原始論文。

參考資源

• DINOv2論文
• DPT論文

使用Transformers庫調用模型

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-large-kitti")
model = DPTForDepthEstimation.from_pretrained("facebook/dpt-dinov2-large-kitti")

# 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)

💻 使用示例

基礎用法

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-large-kitti")
model = DPTForDepthEstimation.from_pretrained("facebook/dpt-dinov2-large-kitti")

# 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)

📄 許可證

本模型使用Apache-2.0許可證。

模型使用說明

預期用途

該模型旨在展示使用DPT框架並以DINOv2作為主幹網絡可以得到一個強大的深度估計器。

BibTeX引用和引用信息

@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}
}