File size: 4,196 Bytes
a1fd9eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5edc8b8
 
a1fd9eb
5edc8b8
 
 
 
 
a1fd9eb
15683b1
 
0e305c3
a1fd9eb
15683b1
5edc8b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e305c3
 
5edc8b8
 
 
 
 
 
 
 
 
 
 
 
 
0e305c3
 
 
 
 
 
 
5edc8b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1fd9eb
 
15683b1
 
5edc8b8
 
15683b1
 
97383d6
5edc8b8
97383d6
15683b1
 
5edc8b8
15683b1
a1fd9eb
 
 
5edc8b8
a1fd9eb
5edc8b8
a1fd9eb
5edc8b8
15683b1
5edc8b8
 
 
a1fd9eb
 
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
134
135
136
137
138
139
140
141
142
143
144
<!DOCTYPE html>
<html>
    <head>
        <meta charset="utf-8">
        <meta name="viewport" content="width=device-width, initial-scale=1">
        <title>Gradio-Lite: Serverless Gradio Running Entirely in Your Browser</title>
        <meta name="description" content="Gradio-Lite: Serverless Gradio Running Entirely in Your Browser">

        <script type="module" crossorigin src="https://cdn.jsdelivr.net/npm/@gradio/lite/dist/lite.js"></script>
        <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@gradio/lite/dist/lite.css" />

        <style>
            html, body {
                margin: 0;
                padding: 0;
                height: 100%;
            }
        </style>
    </head>
    <body>
		<gradio-lite>
			<gradio-file name="app.py" entrypoint>
import gradio as gr
import numpy as np
import PIL
import trimesh
from transformers_js import import_transformers_js, as_url


transformers = await import_transformers_js()
pipeline = transformers.pipeline
depth_estimator = await pipeline('depth-estimation', 'Xenova/depth-anything-small-hf');


def depthmap_to_glb_trimesh(depth_map, rgb_image, file_path):
    assert depth_map.shape[:2] == rgb_image.shape[:2], "Depth map and RGB image must have the same dimensions"

    # Generate vertices and faces
    vertices = []
    colors = []
    faces = []

    height, width = depth_map.shape
    for y in range(height):
        for x in range(width):
            z = depth_map[y, x]
            vertices.append([x, y, z])
            colors.append(rgb_image[y, x])

    # Create faces (2 triangles per pixel, except for edges)
    for y in range(height - 1):
        for x in range(width - 1):
            top_left = y * width + x
            top_right = top_left + 1
            bottom_left = top_left + width
            bottom_right = bottom_left + 1

            faces.append([top_left, bottom_left, top_right])
            faces.append([top_right, bottom_left, bottom_right])

    # Convert to numpy arrays
    vertices = np.array(vertices, dtype=np.float64)
    colors = np.array(colors, dtype=np.uint8)
    faces = np.array(faces, dtype=np.int32)

    mesh = trimesh.Trimesh(vertices=vertices, faces=faces, vertex_colors=colors, process=False)

    # Export to GLB
    mesh.export(file_path, file_type='glb')


def invert_depth(depth_map):
    max_depth = np.max(depth_map)
    return max_depth - depth_map


def invert_xy(map):
    return map[::-1, ::-1]


async def estimate(image_path, depth_scale):
    image = PIL.Image.open(image_path)
    image.thumbnail((384, 384)) # Resize the image keeping the aspect ratio

    predictions = await depth_estimator(as_url(image_path))

    depth_image = predictions["depth"].to_pil()

    tensor = predictions["predicted_depth"]
    tensor_data = {
        "dims": tensor.dims,
        "type": tensor.type,
        "data": tensor.data,
        "size": tensor.size,
    }

		# Construct the 3D model from the depth map and the RGB image
    depth = predictions["predicted_depth"].numpy()
    depth = invert_depth(depth)
    depth = invert_xy(depth)

    depth = depth * depth_scale

    # The model outputs the depth map in a different size than the input image.
    # So we resize the depth map to match the original image size.
    depth = np.array(PIL.Image.fromarray(depth).resize(image.size))

    image_array = np.asarray(image)
    image_array = invert_xy(image_array)

    glb_file_path = "output.glb"
    depthmap_to_glb_trimesh(depth, image_array, glb_file_path)

    return depth_image, glb_file_path, tensor_data


demo = gr.Interface(
    fn=estimate,
    inputs=[
        gr.Image(type="filepath"),
        gr.Slider(minimum=1, maximum=100, value=10, label="Depth Scale")
    ],
    outputs=[
        gr.Image(label="Depth Image"),
        gr.Model3D(label="3D Model"),
        gr.JSON(label="Tensor"),
    ],
    examples=[
        ["bread_small.png"],
    ]
)

demo.launch()
			</gradio-file>

			<gradio-file name="bread_small.png" url="https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/bread_small.png" />

			<gradio-requirements>
transformers_js_py
trimesh
			</gradio-requirements>
		</gradio-lite>
    </body>
</html>