Depth-Anything-V2/run_video.py at main · isl-org/Depth-Anything-V2 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
import argparse
import cv2
import glob
import matplotlib
import numpy as np
import os
import torch

from depth_anything_v2.dpt import DepthAnythingV2


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Depth Anything V2")

    parser.add_argument("--video-path", type=str)
    parser.add_argument("--input-size", type=int, default=518)
    parser.add_argument("--outdir", type=str, default="./vis_video_depth")

    parser.add_argument(
        "--encoder", type=str, default="vitl", choices=["vits", "vitb", "vitl", "vitg"]
    )

    parser.add_argument(
        "--pred-only",
        dest="pred_only",
        action="store_true",
        help="only display the prediction",
    )
    parser.add_argument(
        "--grayscale",
        dest="grayscale",
        action="store_true",
        help="do not apply colorful palette",
    )
    parser.add_argument("--ckptdir", type=str, default=f"checkpoints")

    args = parser.parse_args()

    DEVICE = (
        "cuda"
        if torch.cuda.is_available()
        else "mps" if torch.backends.mps.is_available() else "cpu"
    )

    model_configs = {
        "vits": {"encoder": "vits", "features": 64, "out_channels": [48, 96, 192, 384]},
        "vitb": {
            "encoder": "vitb",
            "features": 128,
            "out_channels": [96, 192, 384, 768],
        },
        "vitl": {
            "encoder": "vitl",
            "features": 256,
            "out_channels": [256, 512, 1024, 1024],
        },
        "vitg": {
            "encoder": "vitg",
            "features": 384,
            "out_channels": [1536, 1536, 1536, 1536],
        },
    }
    ckpt_path = os.path.join(args.ckptdir, f"depth_anything_v2_{args.encoder}.pth")

    depth_anything = DepthAnythingV2(**model_configs[args.encoder])
    depth_anything.load_state_dict(torch.load(ckpt_path, map_location="cpu"))
    depth_anything = depth_anything.to(DEVICE).eval()

    if os.path.isfile(args.video_path):
        if args.video_path.endswith("txt"):
            with open(args.video_path, "r") as f:
                filenames = f.read().splitlines()
        else:
            filenames = [args.video_path]
    else:
        filenames = glob.glob(os.path.join(args.video_path, "**/*"), recursive=True)

    os.makedirs(args.outdir, exist_ok=True)

    margin_width = 50
    cmap = matplotlib.colormaps.get_cmap("Spectral_r")

    for k, filename in enumerate(filenames):
        print(f"Progress {k+1}/{len(filenames)}: {filename}")

        raw_video = cv2.VideoCapture(filename)
        frame_width, frame_height = int(raw_video.get(cv2.CAP_PROP_FRAME_WIDTH)), int(
            raw_video.get(cv2.CAP_PROP_FRAME_HEIGHT)
        )
        frame_rate = int(raw_video.get(cv2.CAP_PROP_FPS))

        if args.pred_only:
            output_width = frame_width
        else:
            output_width = frame_width * 2 + margin_width

        output_path = os.path.join(
            args.outdir, os.path.splitext(os.path.basename(filename))[0] + ".mp4"
        )
        out = cv2.VideoWriter(
            output_path,
            cv2.VideoWriter_fourcc(*"mp4v"),
            frame_rate,
            (output_width, frame_height),
        )

        while raw_video.isOpened():
            ret, raw_frame = raw_video.read()
            if not ret:
                break

            depth = depth_anything.infer_image(raw_frame, args.input_size)

            depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
            depth = depth.astype(np.uint8)

            if args.grayscale:
                depth = np.repeat(depth[..., np.newaxis], 3, axis=-1)
            else:
                depth = (cmap(depth)[:, :, :3] * 255)[:, :, ::-1].astype(np.uint8)

            if args.pred_only:
                out.write(depth)
            else:
                split_region = (
                    np.ones((frame_height, margin_width, 3), dtype=np.uint8) * 255
                )
                combined_frame = cv2.hconcat([raw_frame, split_region, depth])

                out.write(combined_frame)

        raw_video.release()
        out.release()