File size: 7,128 Bytes
4026aa0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
import logging
import os
import tempfile
import time

import gradio as gr
import numpy as np
import rembg
import torch
from PIL import Image
from functools import partial

from tsr.system import TSR
from tsr.utils import remove_background, resize_foreground, to_gradio_3d_orientation

import argparse


if torch.cuda.is_available():
    device = "cuda:0"
else:
    device = "cpu"

model = TSR.from_pretrained(
    "stabilityai/TripoSR",
    config_name="config.yaml",
    weight_name="model.ckpt",
)

# adjust the chunk size to balance between speed and memory usage
model.renderer.set_chunk_size(8192)
model.to(device)

rembg_session = rembg.new_session()


def check_input_image(input_image):
    if input_image is None:
        raise gr.Error("No image uploaded!")


def preprocess(input_image, do_remove_background, foreground_ratio):
    def fill_background(image):
        image = np.array(image).astype(np.float32) / 255.0
        image = image[:, :, :3] * image[:, :, 3:4] + (1 - image[:, :, 3:4]) * 0.5
        image = Image.fromarray((image * 255.0).astype(np.uint8))
        return image

    if do_remove_background:
        image = input_image.convert("RGB")
        image = remove_background(image, rembg_session)
        image = resize_foreground(image, foreground_ratio)
        image = fill_background(image)
    else:
        image = input_image
        if image.mode == "RGBA":
            image = fill_background(image)
    return image


def generate(image, mc_resolution, formats=["obj", "glb"]):
    scene_codes = model(image, device=device)
    mesh = model.extract_mesh(scene_codes, resolution=mc_resolution)[0]
    mesh = to_gradio_3d_orientation(mesh)
    rv = []
    for format in formats:
        mesh_path = tempfile.NamedTemporaryFile(suffix=f".{format}", delete=False)
        mesh.export(mesh_path.name)
        rv.append(mesh_path.name)
    return rv


def run_example(image_pil):
    preprocessed = preprocess(image_pil, False, 0.9)
    mesh_name_obj, mesh_name_glb = generate(preprocessed, 256, ["obj", "glb"])
    return preprocessed, mesh_name_obj, mesh_name_glb


with gr.Blocks(title="TripoSR") as interface:
    gr.Markdown(
        """
    # TripoSR Demo
    [TripoSR](https://github.com/VAST-AI-Research/TripoSR) is a state-of-the-art open-source model for **fast** feedforward 3D reconstruction from a single image, collaboratively developed by [Tripo AI](https://www.tripo3d.ai/) and [Stability AI](https://stability.ai/).
    
    **Tips:**
    1. If you find the result is unsatisfied, please try to change the foreground ratio. It might improve the results.
    2. You can disable "Remove Background" for the provided examples since they have been already preprocessed.
    3. Otherwise, please disable "Remove Background" option only if your input image is RGBA with transparent background, image contents are centered and occupy more than 70% of image width or height.
    """
    )
    with gr.Row(variant="panel"):
        with gr.Column():
            with gr.Row():
                input_image = gr.Image(
                    label="Input Image",
                    image_mode="RGBA",
                    sources="upload",
                    type="pil",
                    elem_id="content_image",
                )
                processed_image = gr.Image(label="Processed Image", interactive=False)
            with gr.Row():
                with gr.Group():
                    do_remove_background = gr.Checkbox(
                        label="Remove Background", value=True
                    )
                    foreground_ratio = gr.Slider(
                        label="Foreground Ratio",
                        minimum=0.5,
                        maximum=1.0,
                        value=0.85,
                        step=0.05,
                    )
                    mc_resolution = gr.Slider(
                        label="Marching Cubes Resolution",
                        minimum=32,
                        maximum=320,
                        value=256,
                        step=32
                    )
            with gr.Row():
                submit = gr.Button("Generate", elem_id="generate", variant="primary")
        with gr.Column():
            with gr.Tab("OBJ"):
                output_model_obj = gr.Model3D(
                    label="Output Model (OBJ Format)",
                    interactive=False,
                )
                gr.Markdown("Note: The model shown here is flipped. Download to get correct results.")
            with gr.Tab("GLB"):
                output_model_glb = gr.Model3D(
                    label="Output Model (GLB Format)",
                    interactive=False,
                )
                gr.Markdown("Note: The model shown here has a darker appearance. Download to get correct results.")
    with gr.Row(variant="panel"):
        gr.Examples(
            examples=[
                "examples/hamburger.png",
                "examples/poly_fox.png",
                "examples/robot.png",
                "examples/teapot.png",
                "examples/tiger_girl.png",
                "examples/horse.png",
                "examples/flamingo.png",
                "examples/unicorn.png",
                "examples/chair.png",
                "examples/iso_house.png",
                "examples/marble.png",
                "examples/police_woman.png",
                "examples/captured_p.png",
            ],
            inputs=[input_image],
            outputs=[processed_image, output_model_obj, output_model_glb],
            cache_examples=False,
            fn=partial(run_example),
            label="Examples",
            examples_per_page=20,
        )
    submit.click(fn=check_input_image, inputs=[input_image]).success(
        fn=preprocess,
        inputs=[input_image, do_remove_background, foreground_ratio],
        outputs=[processed_image],
    ).success(
        fn=generate,
        inputs=[processed_image, mc_resolution],
        outputs=[output_model_obj, output_model_glb],
    )



if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--username', type=str, default=None, help='Username for authentication')
    parser.add_argument('--password', type=str, default=None, help='Password for authentication')
    parser.add_argument('--port', type=int, default=8005, help='Port to run the server listener on')
    parser.add_argument("--listen", action='store_true', default="0.0.0.0", help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
    parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site")
    parser.add_argument("--queuesize", type=int, default=1, help="launch gradio queue max_size")
    args = parser.parse_args()
    interface.queue(max_size=args.queuesize)
    interface.launch(
        auth=(args.username, args.password) if (args.username and args.password) else None,
        share=args.share,
        server_name="0.0.0.0" if args.listen else None, 
        server_port=args.port
    )