Apple Depth Pro：1枚の画像から鮮明なメトリック深度

import { AutoModelForDepthEstimation, AutoProcessor, RawImage } from "@huggingface/transformers";

const id = "onnx-community/DepthPro-ONNX";
const processor = await AutoProcessor.from_pretrained(id);
const model = await AutoModelForDepthEstimation.from_pretrained(id, { device: "webgpu", dtype: "q4f16" });

const image = await RawImage.read("photo.jpg");
const { predicted_depth, focallength_px } = await model(await processor(image));
// predicted_depth: metric depth (metres); resize to the input and normalise for display.

import torch
from PIL import Image
from transformers import DepthProForDepthEstimation, DepthProImageProcessorFast

device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
processor = DepthProImageProcessorFast.from_pretrained("apple/DepthPro-hf")
model = DepthProForDepthEstimation.from_pretrained("apple/DepthPro-hf").to(device).eval()

image = Image.open("photo.jpg").convert("RGB")
inputs = processor(images=image, return_tensors="pt").to(device)
with torch.no_grad():
    outputs = model(**inputs)

post = processor.post_process_depth_estimation(outputs, target_sizes=[(image.height, image.width)])[0]
depth_m = post["predicted_depth"]          # metres, shape (H, W)
focal_px = float(post["focal_length"])     # estimated focal length in pixels
print(depth_m.min().item(), depth_m.max().item(), focal_px)

git clone https://github.com/apple/ml-depth-pro.git
cd ml-depth-pro
conda create -n depth-pro -y python=3.9
conda activate depth-pro
pip install -e .
source get_pretrained_models.sh          # downloads checkpoints/depth_pro.pt
depth-pro-run -i ./data/example.jpg      # writes a depth map next to the input