Distill Any Depth Small Hf

🚀 輕量級深度蒸餾模型 - Transformers版本

Distill-Any-Depth是一種全新的單目深度估計模型，它採用了我們提出的知識蒸餾算法進行訓練，達到了當前最優水平（SOTA）。該模型在論文 Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator 中被首次提出。此模型的檢查點與transformers庫兼容，你可以通過 在線演示 體驗其效果。

🚀 快速開始

以下是使用該模型進行零樣本深度估計的方法：

基礎用法

from transformers import pipeline
from PIL import Image
import requests
# load pipe
pipe = pipeline(task="depth-estimation", model="xingyang1/Distill-Any-Depth-Small-hf")
# load image
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
# inference
depth = pipe(image)["depth"]

高級用法

from transformers import AutoImageProcessor, AutoModelForDepthEstimation
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("xingyang1/Distill-Any-Depth-Small-hf")
model = AutoModelForDepthEstimation.from_pretrained("xingyang1/Distill-Any-Depth-Small-hf")

# prepare image for the model
inputs = image_processor(images=image, return_tensors="pt")

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

# interpolate to original size and visualize the prediction
post_processed_output = image_processor.post_process_depth_estimation(
    outputs,
    target_sizes=[(image.height, image.width)],
)

predicted_depth = post_processed_output[0]["predicted_depth"]
depth = (predicted_depth - predicted_depth.min()) / (predicted_depth.max() - predicted_depth.min())
depth = depth.detach().cpu().numpy() * 255
depth = Image.fromarray(depth.astype("uint8"))

📄 許可證

本項目採用MIT許可證。

📚 詳細文檔

如果你覺得這個項目有用，請考慮引用以下文獻：

@article{he2025distill,
  title   = {Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator},
  author  = {Xiankang He and Dongyan Guo and Hongji Li and Ruibo Li and Ying Cui and Chi Zhang},
  year    = {2025},
  journal = {arXiv preprint arXiv: 2502.19204}
}

👨‍💻 模型卡片作者

Parteek Kamboj

📋 模型信息