File size: 13,140 Bytes
9223079
 
cd1bd30
9223079
8e76240
7b977a8
 
 
8e76240
 
 
 
 
 
 
 
9223079
 
7b977a8
 
 
c74a070
7b977a8
9223079
fd74792
49a0323
 
7b977a8
9223079
 
 
8e76240
 
 
 
 
 
 
 
 
 
 
7e8852b
8e76240
 
9223079
 
8e76240
 
 
 
 
 
 
 
9223079
8e76240
 
 
 
 
 
 
 
 
42dde81
 
 
8e76240
 
 
 
 
 
 
 
 
9223079
 
 
7b977a8
e3598ee
8e76240
 
 
 
 
 
 
 
 
7b977a8
 
9223079
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8e76240
 
9223079
 
 
 
 
8e76240
 
9223079
 
 
49a0323
8e76240
9223079
7b977a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
7b977a8
42dde81
7b977a8
 
8e76240
7b977a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e15a186
7b977a8
 
 
 
 
8e76240
7b977a8
9223079
7b977a8
9223079
 
7b977a8
 
9223079
 
 
 
7b977a8
 
 
 
 
9223079
 
 
 
 
 
7b977a8
9223079
 
 
7b977a8
 
 
 
 
 
 
 
 
 
 
 
9223079
 
 
42dde81
 
 
 
7b977a8
 
42dde81
7b977a8
 
 
 
42dde81
 
 
 
8e76240
 
 
 
 
 
 
9223079
 
7b977a8
 
 
9223079
 
7b977a8
 
 
9223079
 
 
 
42dde81
 
 
9223079
 
7b977a8
 
9223079
 
 
 
 
 
7b977a8
 
9223079
 
 
 
 
 
 
42dde81
 
 
9223079
 
7b977a8
 
 
 
 
 
 
9223079
7b977a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a443266
9223079
 
 
 
 
e3598ee
7b977a8
e3598ee
 
 
 
 
 
 
 
9223079
e3598ee
9223079
e3598ee
 
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
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
import argparse
import gradio as gr
from common.utils import (
    matcher_zoo,
    ransac_zoo,
    change_estimate_geom,
    run_matching,
    gen_examples,
    DEFAULT_RANSAC_METHOD,
    DEFAULT_SETTING_GEOMETRY,
    DEFAULT_RANSAC_REPROJ_THRESHOLD,
    DEFAULT_RANSAC_CONFIDENCE,
    DEFAULT_RANSAC_MAX_ITER,
    DEFAULT_MATCHING_THRESHOLD,
    DEFAULT_SETTING_MAX_FEATURES,
    DEFAULT_DEFAULT_KEYPOINT_THRESHOLD,
)

DESCRIPTION = """
# Image Matching WebUI
This Space demonstrates [Image Matching WebUI](https://github.com/Vincentqyw/image-matching-webui) by vincent qin. Feel free to play with it, or duplicate to run image matching without a queue!

πŸ”Ž For more details about supported local features and matchers, please refer to https://github.com/Vincentqyw/image-matching-webui

πŸš€ All algorithms run on CPU for inference on HF, causing slow speeds and high latency. For faster inference, please download the [source code](https://github.com/Vincentqyw/image-matching-webui) for local deployment.

πŸ› Your feedback is valuable to me. Please do not hesitate to report any bugs [here](https://github.com/Vincentqyw/image-matching-webui/issues).
"""


def ui_change_imagebox(choice):
    """
    Updates the image box with the given choice.

    Args:
        choice (list): The list of image sources to be displayed in the image box.

    Returns:
        dict: A dictionary containing the updated value, sources, and type for the image box.
    """
    return {
        "value": None,  # The updated value of the image box
        "source": choice,  # The list of image sources to be displayed
        "__type__": "update",  # The type of update for the image box
    }


def ui_reset_state(*args):
    """
    Reset the state of the UI.

    Returns:
        tuple: A tuple containing the initial values for the UI state.
    """
    key = list(matcher_zoo.keys())[0]  # Get the first key from matcher_zoo
    return (
        None,  # image0
        None,  # image1
        DEFAULT_MATCHING_THRESHOLD,  # matching_threshold
        DEFAULT_SETTING_MAX_FEATURES,  # max_features
        DEFAULT_DEFAULT_KEYPOINT_THRESHOLD,  # keypoint_threshold
        key,  # matcher
        ui_change_imagebox("upload"),  # input image0
        ui_change_imagebox("upload"),  # input image1
        "upload",  # match_image_src
        None,  # keypoints
        None,  # raw matches
        None,  # ransac matches
        {},  # matches result info
        {},  # matcher config
        None,  # warped image
        {},  # geometry result
        DEFAULT_RANSAC_METHOD,  # ransac_method
        DEFAULT_RANSAC_REPROJ_THRESHOLD,  # ransac_reproj_threshold
        DEFAULT_RANSAC_CONFIDENCE,  # ransac_confidence
        DEFAULT_RANSAC_MAX_ITER,  # ransac_max_iter
        DEFAULT_SETTING_GEOMETRY,  # geometry
    )


# "footer {visibility: hidden}"
def run(server_name="127.0.0.1", server_port=7860):
    """
    Runs the application.

    Args:
        config (dict): A dictionary containing configuration parameters for the application.

    Returns:
        None
    """
    with gr.Blocks(css="style.css") as app:
        gr.Markdown(DESCRIPTION)

        with gr.Row(equal_height=False):
            with gr.Column():
                with gr.Row():
                    matcher_list = gr.Dropdown(
                        choices=list(matcher_zoo.keys()),
                        value="disk+lightglue",
                        label="Matching Model",
                        interactive=True,
                    )
                    match_image_src = gr.Radio(
                        ["upload", "webcam", "canvas"],
                        label="Image Source",
                        value="upload",
                    )
                with gr.Row():
                    input_image0 = gr.Image(
                        label="Image 0",
                        type="numpy",
                        image_mode="RGB",
                        height=300,
                        interactive=True,
                    )
                    input_image1 = gr.Image(
                        label="Image 1",
                        type="numpy",
                        image_mode="RGB",
                        height=300,
                        interactive=True,
                    )

                with gr.Row():
                    button_reset = gr.Button(value="Reset")
                    button_run = gr.Button(value="Run Match", variant="primary")

                with gr.Accordion("Advanced Setting", open=False):
                    with gr.Accordion("Matching Setting", open=True):
                        with gr.Row():
                            match_setting_threshold = gr.Slider(
                                minimum=0.0,
                                maximum=1,
                                step=0.001,
                                label="Match thres.",
                                value=0.1,
                            )
                            match_setting_max_features = gr.Slider(
                                minimum=10,
                                maximum=10000,
                                step=10,
                                label="Max features",
                                value=1000,
                            )
                        # TODO: add line settings
                        with gr.Row():
                            detect_keypoints_threshold = gr.Slider(
                                minimum=0,
                                maximum=1,
                                step=0.001,
                                label="Keypoint thres.",
                                value=0.015,
                            )
                            detect_line_threshold = gr.Slider(
                                minimum=0.1,
                                maximum=1,
                                step=0.01,
                                label="Line thres.",
                                value=0.2,
                            )
                        # matcher_lists = gr.Radio(
                        #     ["NN-mutual", "Dual-Softmax"],
                        #     label="Matcher mode",
                        #     value="NN-mutual",
                        # )
                    with gr.Accordion("RANSAC Setting", open=True):
                        with gr.Row(equal_height=False):
                            # enable_ransac = gr.Checkbox(label="Enable RANSAC")
                            ransac_method = gr.Dropdown(
                                choices=ransac_zoo.keys(),
                                value=DEFAULT_RANSAC_METHOD,
                                label="RANSAC Method",
                                interactive=True,
                            )
                        ransac_reproj_threshold = gr.Slider(
                            minimum=0.0,
                            maximum=12,
                            step=0.01,
                            label="Ransac Reproj threshold",
                            value=8.0,
                        )
                        ransac_confidence = gr.Slider(
                            minimum=0.0,
                            maximum=1,
                            step=0.00001,
                            label="Ransac Confidence",
                            value=0.99999,
                        )
                        ransac_max_iter = gr.Slider(
                            minimum=0.0,
                            maximum=100000,
                            step=100,
                            label="Ransac Iterations",
                            value=10000,
                        )

                    with gr.Accordion("Geometry Setting", open=False):
                        with gr.Row(equal_height=False):
                            # show_geom = gr.Checkbox(label="Show Geometry")
                            choice_estimate_geom = gr.Radio(
                                ["Fundamental", "Homography"],
                                label="Reconstruct Geometry",
                                value=DEFAULT_SETTING_GEOMETRY,
                            )

                # with gr.Column():
                # collect inputs
                inputs = [
                    input_image0,
                    input_image1,
                    match_setting_threshold,
                    match_setting_max_features,
                    detect_keypoints_threshold,
                    matcher_list,
                    ransac_method,
                    ransac_reproj_threshold,
                    ransac_confidence,
                    ransac_max_iter,
                    choice_estimate_geom,
                ]

                # Add some examples
                with gr.Row():
                    # Example inputs
                    gr.Examples(
                        examples=gen_examples(),
                        inputs=inputs,
                        outputs=[],
                        fn=run_matching,
                        cache_examples=False,
                        label=(
                            "Examples (click one of the images below to Run"
                            " Match)"
                        ),
                    )
                with gr.Accordion("Open for More!", open=False):
                    gr.Markdown(
                        f"""
                        <h3>Supported Algorithms</h3>
                        {", ".join(matcher_zoo.keys())}
                        """
                    )

            with gr.Column():
                output_keypoints = gr.Image(label="Keypoints", type="numpy")
                output_matches_raw = gr.Image(label="Raw Matches", type="numpy")
                output_matches_ransac = gr.Image(
                    label="Ransac Matches", type="numpy"
                )
                with gr.Accordion(
                    "Open for More: Matches Statistics", open=False
                ):
                    matches_result_info = gr.JSON(label="Matches Statistics")
                    matcher_info = gr.JSON(label="Match info")

                with gr.Accordion("Open for More: Warped Image", open=False):
                    output_wrapped = gr.Image(
                        label="Wrapped Pair", type="numpy"
                    )
                    with gr.Accordion(
                        "Open for More: Geometry info", open=False
                    ):
                        geometry_result = gr.JSON(
                            label="Reconstructed Geometry"
                        )

            # callbacks
            match_image_src.change(
                fn=ui_change_imagebox,
                inputs=match_image_src,
                outputs=input_image0,
            )
            match_image_src.change(
                fn=ui_change_imagebox,
                inputs=match_image_src,
                outputs=input_image1,
            )

            # collect outputs
            outputs = [
                output_keypoints,
                output_matches_raw,
                output_matches_ransac,
                matches_result_info,
                matcher_info,
                geometry_result,
                output_wrapped,
            ]
            # button callbacks
            button_run.click(fn=run_matching, inputs=inputs, outputs=outputs)

            # Reset images
            reset_outputs = [
                input_image0,
                input_image1,
                match_setting_threshold,
                match_setting_max_features,
                detect_keypoints_threshold,
                matcher_list,
                input_image0,
                input_image1,
                match_image_src,
                output_keypoints,
                output_matches_raw,
                output_matches_ransac,
                matches_result_info,
                matcher_info,
                output_wrapped,
                geometry_result,
                ransac_method,
                ransac_reproj_threshold,
                ransac_confidence,
                ransac_max_iter,
                choice_estimate_geom,
            ]
            button_reset.click(
                fn=ui_reset_state, inputs=inputs, outputs=reset_outputs
            )

            # estimate geo
            choice_estimate_geom.change(
                fn=change_estimate_geom,
                inputs=[
                    input_image0,
                    input_image1,
                    geometry_result,
                    choice_estimate_geom,
                ],
                outputs=[output_wrapped, geometry_result],
            )
    app.queue().launch(share=False)


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--server_name",
        type=str,
        default="127.0.0.1",
        help="server name",
    )
    parser.add_argument(
        "--server_port",
        type=int,
        default=7860,
        help="server port",
    )

    args = parser.parse_args()
    run(args.server_name, args.server_port)