Spaces:
Sleeping
Sleeping
File size: 31,631 Bytes
7acaad7 8320ccc 7acaad7 8320ccc 5069bec 7acaad7 8320ccc 7acaad7 4a7fc02 e9f6961 7acaad7 7419d98 7acaad7 2507d2f 7acaad7 2507d2f 7acaad7 2507d2f 7acaad7 2507d2f 7acaad7 2507d2f 8320ccc 2507d2f 7acaad7 2507d2f 7acaad7 2507d2f 7acaad7 2507d2f 7acaad7 2507d2f 7acaad7 2507d2f 7acaad7 2507d2f e9f6961 2507d2f e9f6961 2507d2f 68a65da 2507d2f 7acaad7 2507d2f e9f6961 2507d2f 4a7fc02 e9f6961 2507d2f 7acaad7 2507d2f 68a65da 2507d2f 7acaad7 2507d2f 7acaad7 3c77caa 68a65da 7acaad7 2507d2f 7acaad7 2507d2f 68a65da 2507d2f 7acaad7 2507d2f e9f6961 2507d2f 7acaad7 e8c2e78 2507d2f 7acaad7 2507d2f e8c2e78 7acaad7 68a65da 7acaad7 2d36d99 6ae8c1a 2d36d99 10dcc2e 2d36d99 3c77caa 2d36d99 3c77caa 2d36d99 b5957bd 2d36d99 e8c2e78 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 |
from pathlib import Path
from typing import Any, Dict, Optional, Tuple
import gradio as gr
import numpy as np
from common.utils import (
GRADIO_VERSION,
gen_examples,
generate_warp_images,
get_matcher_zoo,
load_config,
ransac_zoo,
run_matching,
run_ransac,
send_to_match,
)
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!
<br/>
🔎 For more details about supported local features and matchers, please refer to https://github.com/Vincentqyw/image-matching-webui
🚀 All algorithms run on CPU for inference, causing slow speeds and high latency. For faster inference, please download the [source code](https://github.com/Vincentqyw/image-matching-webui) for local deployment.
🐛 Your feedback is valuable to me. Please do not hesitate to report any bugs [here](https://github.com/Vincentqyw/image-matching-webui/issues).
"""
class ImageMatchingApp:
def __init__(self, server_name="0.0.0.0", server_port=7860, **kwargs):
self.server_name = server_name
self.server_port = server_port
self.config_path = kwargs.get(
"config", Path(__file__).parent / "config.yaml"
)
self.cfg = load_config(self.config_path)
self.matcher_zoo = get_matcher_zoo(self.cfg["matcher_zoo"])
self.app = None
self.init_interface()
# print all the keys
def init_matcher_dropdown(self):
algos = []
for k, v in self.cfg["matcher_zoo"].items():
if v.get("enable", True):
algos.append(k)
return algos
def init_interface(self):
with gr.Blocks() as self.app:
with gr.Tab("Image Matching"):
with gr.Row():
with gr.Column(scale=1):
gr.Image(
str(
Path(__file__).parent.parent
/ "assets/logo.webp"
),
elem_id="logo-img",
show_label=False,
show_share_button=False,
show_download_button=False,
)
with gr.Column(scale=3):
gr.Markdown(DESCRIPTION)
with gr.Row(equal_height=False):
with gr.Column():
with gr.Row():
matcher_list = gr.Dropdown(
choices=self.init_matcher_dropdown(),
value="disk+lightglue",
label="Matching Model",
interactive=True,
)
match_image_src = gr.Radio(
(
["upload", "webcam", "clipboard"]
if GRADIO_VERSION > "3"
else ["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 if GRADIO_VERSION > "3" else None,
interactive=True,
)
input_image1 = gr.Image(
label="Image 1",
type="numpy",
image_mode="RGB",
height=300 if GRADIO_VERSION > "3" else None,
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 = ( # noqa: F841
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):
ransac_method = gr.Dropdown(
choices=ransac_zoo.keys(),
value=self.cfg["defaults"][
"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=self.cfg["defaults"][
"ransac_confidence"
],
)
ransac_max_iter = gr.Slider(
minimum=0.0,
maximum=100000,
step=100,
label="Ransac Iterations",
value=self.cfg["defaults"][
"ransac_max_iter"
],
)
button_ransac = gr.Button(
value="Rerun RANSAC", variant="primary"
)
with gr.Accordion("Geometry Setting", open=False):
with gr.Row(equal_height=False):
choice_geometry_type = gr.Radio(
["Fundamental", "Homography"],
label="Reconstruct Geometry",
value=self.cfg["defaults"][
"setting_geometry"
],
)
# collect inputs
state_cache = gr.State({})
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_geometry_type,
gr.State(self.matcher_zoo),
# state_cache,
]
# Add some examples
with gr.Row():
# Example inputs
with gr.Accordion(
"Open for More: Examples", open=True
):
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). Thx: WxBS"
),
)
with gr.Accordion("Supported Algorithms", open=False):
# add a table of supported algorithms
self.display_supported_algorithms()
with gr.Column():
with gr.Accordion(
"Open for More: Keypoints", open=True
):
output_keypoints = gr.Image(
label="Keypoints", type="numpy"
)
with gr.Accordion(
"Open for More: Raw Matches", open=False
):
output_matches_raw = gr.Image(
label="Raw Matches",
type="numpy",
)
with gr.Accordion(
"Open for More: RANSAC Matches", open=True
):
output_matches_ransac = gr.Image(
label="Ransac Matches", type="numpy"
)
with gr.Accordion(
"Open for More: Matches Statistics", open=False
):
output_pred = gr.File(
label="Outputs", elem_id="download"
)
matches_result_info = gr.JSON(
label="Matches Statistics"
)
matcher_info = gr.JSON(label="Match info")
with gr.Accordion(
"Open for More: Warped Image", open=True
):
output_wrapped = gr.Image(
label="Wrapped Pair", type="numpy"
)
# send to input
button_rerun = gr.Button(
value="Send to Input Match Pair",
variant="primary",
)
with gr.Accordion(
"Open for More: Geometry info", open=False
):
geometry_result = gr.JSON(
label="Reconstructed Geometry"
)
# callbacks
match_image_src.change(
fn=self.ui_change_imagebox,
inputs=match_image_src,
outputs=input_image0,
)
match_image_src.change(
fn=self.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,
state_cache,
output_pred,
]
# 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_geometry_type,
output_pred,
]
button_reset.click(
fn=self.ui_reset_state,
inputs=None,
outputs=reset_outputs,
)
# run ransac button action
button_ransac.click(
fn=run_ransac,
inputs=[
state_cache,
choice_geometry_type,
ransac_method,
ransac_reproj_threshold,
ransac_confidence,
ransac_max_iter,
],
outputs=[
output_matches_ransac,
matches_result_info,
output_wrapped,
output_pred,
],
)
# send warped image to match
button_rerun.click(
fn=send_to_match,
inputs=[state_cache],
outputs=[input_image0, input_image1],
)
# estimate geo
choice_geometry_type.change(
fn=generate_warp_images,
inputs=[
input_image0,
input_image1,
geometry_result,
choice_geometry_type,
],
outputs=[output_wrapped, geometry_result],
)
with gr.Tab("Structure from Motion(under-dev)"):
self.init_tab_sfm()
def init_tab_sfm(self):
sfm_ui = AppSfmUI()
sfm_ui.set_local_features(["disk", "superpoint"])
sfm_ui.set_matchers(["disk+lightglue", "superpoint+lightglue"])
sfm_ui.set_global_features(["netvlad", "mixvpr"])
sfm_ui.call()
def run(self):
self.app.queue().launch(
server_name=self.server_name,
server_port=self.server_port,
share=False,
)
def ui_change_imagebox(self, 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.
"""
ret_dict = {
"value": None, # The updated value of the image box
"__type__": "update", # The type of update for the image box
}
if GRADIO_VERSION > "3":
return {
**ret_dict,
"sources": choice, # The list of image sources to be displayed
}
else:
return {
**ret_dict,
"source": choice, # The list of image sources to be displayed
}
def ui_reset_state(
self,
*args: Any,
) -> Tuple[
Optional[np.ndarray],
Optional[np.ndarray],
float,
int,
float,
str,
Dict[str, Any],
Dict[str, Any],
str,
Optional[np.ndarray],
Optional[np.ndarray],
Optional[np.ndarray],
Dict[str, Any],
Dict[str, Any],
Optional[np.ndarray],
Dict[str, Any],
str,
int,
float,
int,
]:
"""
Reset the state of the UI.
Returns:
tuple: A tuple containing the initial values for the UI state.
"""
key: str = list(self.matcher_zoo.keys())[
0
] # Get the first key from matcher_zoo
return (
None, # image0: Optional[np.ndarray]
None, # image1: Optional[np.ndarray]
self.cfg["defaults"][
"match_threshold"
], # matching_threshold: float
self.cfg["defaults"]["max_keypoints"], # max_features: int
self.cfg["defaults"][
"keypoint_threshold"
], # keypoint_threshold: float
key, # matcher: str
self.ui_change_imagebox("upload"), # input image0: Dict[str, Any]
self.ui_change_imagebox("upload"), # input image1: Dict[str, Any]
"upload", # match_image_src: str
None, # keypoints: Optional[np.ndarray]
None, # raw matches: Optional[np.ndarray]
None, # ransac matches: Optional[np.ndarray]
{}, # matches result info: Dict[str, Any]
{}, # matcher config: Dict[str, Any]
None, # warped image: Optional[np.ndarray]
{}, # geometry result: Dict[str, Any]
self.cfg["defaults"]["ransac_method"], # ransac_method: str
self.cfg["defaults"][
"ransac_reproj_threshold"
], # ransac_reproj_threshold: float
self.cfg["defaults"][
"ransac_confidence"
], # ransac_confidence: float
self.cfg["defaults"]["ransac_max_iter"], # ransac_max_iter: int
self.cfg["defaults"]["setting_geometry"], # geometry: str
None, # predictions
)
def display_supported_algorithms(self, style="tab"):
def get_link(link, tag="Link"):
return "[{}]({})".format(tag, link) if link is not None else "None"
data = []
cfg = self.cfg["matcher_zoo"]
if style == "md":
markdown_table = "| Algo. | Conference | Code | Project | Paper |\n"
markdown_table += (
"| ----- | ---------- | ---- | ------- | ----- |\n"
)
for k, v in cfg.items():
if not v["info"]["display"]:
continue
github_link = get_link(v["info"]["github"])
project_link = get_link(v["info"]["project"])
paper_link = get_link(
v["info"]["paper"],
(
Path(v["info"]["paper"]).name[-10:]
if v["info"]["paper"] is not None
else "Link"
),
)
markdown_table += "{}|{}|{}|{}|{}\n".format(
v["info"]["name"], # display name
v["info"]["source"],
github_link,
project_link,
paper_link,
)
return gr.Markdown(markdown_table)
elif style == "tab":
for k, v in cfg.items():
if not v["info"].get("display", True):
continue
data.append(
[
v["info"]["name"],
v["info"]["source"],
v["info"]["github"],
v["info"]["paper"],
v["info"]["project"],
]
)
tab = gr.Dataframe(
headers=["Algo.", "Conference", "Code", "Paper", "Project"],
datatype=["str", "str", "str", "str", "str"],
col_count=(5, "fixed"),
value=data,
# wrap=True,
# min_width = 1000,
# height=1000,
)
return tab
class AppBaseUI:
def __init__(self, cfg: Dict[str, Any] = None):
self.cfg = cfg
def _init_ui(self):
NotImplemented
def call(self, **kwargs):
self._init_ui()
class AppSfmUI(AppBaseUI):
def __init__(self, cfg: Dict[str, Any] = None):
super().__init__(cfg)
self.matchers = None
self.features = None
self.global_features = None
def _update_options(self, option):
if option == "sparse":
return gr.Textbox("sparse", visible=True)
elif option == "dense":
return gr.Textbox("dense", visible=True)
else:
return gr.Textbox("not set", visible=True)
def set_local_features(self, features):
self.features = features
def set_global_features(self, features):
self.global_features = features
def set_matchers(self, matchers):
self.matchers = matchers
def _on_select_custom_params(self, value: bool = False):
return gr.Textbox(
label="Camera Params",
value="0,0,0,0",
interactive=value,
visible=value,
)
def _init_ui(self):
with gr.Row():
# data settting and camera settings
with gr.Column():
input_images = gr.File(
label="SfM", interactive=True, file_count="multiple"
)
# camera setting
with gr.Accordion("Camera Settings", open=True):
with gr.Column():
with gr.Row():
with gr.Column():
camera_model = gr.Dropdown(
choices=[
"PINHOLE",
"SIMPLE_RADIAL",
"OPENCV",
],
value="PINHOLE",
label="Camera Model",
interactive=True,
)
with gr.Column():
gr.Checkbox(
label="Shared Params",
value=True,
interactive=True,
)
camera_custom_params_cb = gr.Checkbox(
label="Custom Params",
value=False,
interactive=True,
)
with gr.Row():
camera_params = gr.Textbox(
label="Camera Params",
value="0,0,0,0",
interactive=False,
visible=False,
)
camera_custom_params_cb.select(
fn=self._on_select_custom_params,
inputs=camera_custom_params_cb,
outputs=camera_params,
)
with gr.Accordion("Matching Settings", open=True):
# feature extraction and matching setting
with gr.Row():
feature_type = gr.Radio(
["sparse", "dense"],
label="Feature Type",
value="sparse",
interactive=True,
)
feature_details = gr.Textbox(
label="Feature Details",
visible=False,
)
# feature_type.change(
# fn=self._update_options,
# inputs=feature_type,
# outputs=feature_details,
# )
# matcher setting
matcher_name = gr.Dropdown(
choices=self.matchers,
value="disk+lightglue",
label="Matching Model",
interactive=True,
)
with gr.Row():
with gr.Accordion("Advanced Settings", open=False):
with gr.Column():
with gr.Row():
# matching setting
max_features = gr.Slider(
label="Max Features",
minimum=100,
maximum=10000,
value=1000,
interactive=True,
)
ransac_threshold = gr.Slider(
label="Ransac Threshold",
minimum=0.01,
maximum=12.0,
value=4.0,
step=0.01,
interactive=True,
)
with gr.Row():
ransac_confidence = gr.Slider(
label="Ransac Confidence",
minimum=0.01,
maximum=1.0,
value=0.9999,
step=0.0001,
interactive=True,
)
ransac_max_iter = gr.Slider(
label="Ransac Max Iter",
minimum=1,
maximum=100,
value=100,
step=1,
interactive=True,
)
with gr.Accordion("Scene Graph Settings", open=True):
# mapping setting
scene_graph = gr.Dropdown(
choices=["all", "swin", "oneref"],
value="all",
label="Scene Graph",
interactive=True,
)
# global feature setting
global_feature = gr.Dropdown(
choices=self.global_features,
value="netvlad",
label="Global features",
interactive=True,
)
button_match = gr.Button("Run Matching", variant="primary")
# mapping setting
with gr.Column():
with gr.Accordion("Mapping Settings", open=True):
with gr.Row():
with gr.Accordion("Buddle Settings", open=True):
with gr.Row():
mapper_refine_focal_length = gr.Checkbox(
label="Refine Focal Length",
value=False,
interactive=True,
)
mapper_refine_principle_points = gr.Checkbox(
label="Refine Principle Points",
value=False,
interactive=True,
)
mapper_refine_extra_params = gr.Checkbox(
label="Refine Extra Params",
value=False,
interactive=True,
)
with gr.Accordion(
"Retriangluation Settings", open=True
):
gr.Textbox(
label="Retriangluation Details",
)
gr.Button("Run SFM", variant="primary")
model_3d = gr.Model3D()
|