2
6

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 1 year has passed since last update.

画像から深度マップを取得したい

特別なカメラやセンサーやステレオ画像なしで、シンプルに一枚の画像から深度マップを得たい。

Monocular Depth Estimation で取得できる。

Monocular Depth Estimation機械学習モデルMiDaSで、単一画像から深度を取得できる。

pexels-cottonbro-6853517.jpg r (3).png
モデルの初期化。

import torch
model_type = "MiDaS_small"
midas = torch.hub.load("intel-isl/MiDaS", model_type)
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
midas.to(device)
midas.eval()

推論。

img = cv2.imread("pexels-pixabay-164634.jpg")
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

input_batch = transform(img).to(device)
with torch.no_grad():
    prediction = midas(input_batch)

    prediction = torch.nn.functional.interpolate(
        prediction.unsqueeze(1),
        size=img.shape[:2],
        mode="bicubic",
        align_corners=False,
    ).squeeze()

depth = prediction.cpu().numpy()

depth_min = depth.min()
depth_max = depth.max()

max_val = 255

if depth_max - depth_min > np.finfo("float").eps:
    out = max_val * (depth - depth_min) / (depth_max - depth_min)
else:
    out = np.zeros(depth.shape, dtype=depth.type)

cv2.imwrite(path + ".png", out.astype("uint8"))

🐣


フリーランスエンジニアです。
お仕事のご相談こちらまで
rockyshikoku@gmail.com

Core MLやARKitを使ったアプリを作っています。
機械学習/AR関連の情報を発信しています。

Twitter
Medium
GitHub

2
6
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
2
6

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?