pycolmap 3.10.dev0__cp312-cp312-win_amd64.whl

pycolmap-3.10.dev0.dist-info/DELVEWHEEL

@@ -0,0 +1,2 @@
+Version: 1.7.1
+Arguments: ['C:\\Users\\runneradmin\\AppData\\Local\\Temp\\cibw-run-egk5f74t\\cp312-win_amd64\\build\\venv\\Scripts\\delvewheel', 'repair', '-v', '--add-path', 'D:/a/colmap/colmap/build/vcpkg_installed/x64-windows-release/bin', '-w', 'C:\\Users\\runneradmin\\AppData\\Local\\Temp\\cibw-run-egk5f74t\\cp312-win_amd64\\repaired_wheel', 'C:\\Users\\runneradmin\\AppData\\Local\\Temp\\cibw-run-egk5f74t\\cp312-win_amd64\\built_wheel\\pycolmap-3.10.dev0-cp312-cp312-win_amd64.whl']

pycolmap-3.10.dev0.dist-info/METADATA

@@ -0,0 +1,329 @@
+Metadata-Version: 2.1
+Name: pycolmap
+Version: 3.10.dev0
+Summary: COLMAP bindings
+Author-Email: Mihai Dusmanu <mihai.dusmanu@gmail.com>, Paul-Edouard Sarlin <psarlin@ethz.ch>, Philipp Lindenberger <plindenbe@ethz.ch>
+License: BSD-3-Clause
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Programming Language :: Python :: 3 :: Only
+Project-URL: Repository, https://github.com/colmap/pycolmap
+Requires-Python: >=3.7
+Requires-Dist: numpy
+Description-Content-Type: text/markdown
+
+# Python bindings for COLMAP
+
+PyCOLMAP exposes to Python most capabilities of
+[COLMAP](https://colmap.github.io/) for Structure-from-Motion and
+Multiview-stereo, such as reconstruction pipelines & objects and geometric
+estimators.
+
+## Installation
+
+Pre-built wheels for Python 3.8/3.9/3.10 on Linux, macOS 10/11/12 (both Intel
+and Apple Silicon), and Windows can be installed using pip:
+```bash
+pip install pycolmap
+```
+
+The wheels are automatically built and pushed to
+[PyPI](https://pypi.org/project/pycolmap/) at each release. They are currently
+not built with CUDA support, which requires building from source.
+
+<details>
+<summary>[Building PyCOLMAP from source - click to expand]</summary>
+
+1. Install COLMAP from source following [the official guide](https://colmap.github.io/install.html).
+
+3. Build PyCOLMAP:
+  - On Linux and macOS:
+```bash
+python -m pip install .
+```
+  - On Windows, after installing COLMAP [via VCPKG](https://colmap.github.io/install.html#id3), run in powershell:
+```powershell
+python -m pip install . `
+    --cmake.define.CMAKE_TOOLCHAIN_FILE="$VCPKG_INSTALLATION_ROOT/scripts/buildsystems/vcpkg.cmake" `
+    --cmake.define.VCPKG_TARGET_TRIPLET="x64-windows"
+```
+
+</details>
+
+## Reconstruction pipeline
+
+PyCOLMAP provides bindings for multiple steps of the standard reconstruction pipeline:
+
+- extracting and matching SIFT features
+- importing an image folder into a COLMAP database
+- inferring the camera parameters from the EXIF metadata of an image file
+- running two-view geometric verification of matches on a COLMAP database
+- triangulating points into an existing COLMAP model
+- running incremental reconstruction from a COLMAP database
+- dense reconstruction with multi-view stereo
+
+Sparse & Dense reconstruction from a folder of images can be performed with:
+```python
+output_path: pathlib.Path
+image_dir: pathlib.Path
+
+output_path.mkdir()
+mvs_path = output_path / "mvs"
+database_path = output_path / "database.db"
+
+pycolmap.extract_features(database_path, image_dir)
+pycolmap.match_exhaustive(database_path)
+maps = pycolmap.incremental_mapping(database_path, image_dir, output_path)
+maps[0].write(output_path)
+# dense reconstruction
+pycolmap.undistort_images(mvs_path, output_path, image_dir)
+pycolmap.patch_match_stereo(mvs_path)  # requires compilation with CUDA
+pycolmap.stereo_fusion(mvs_path / "dense.ply", mvs_path)
+```
+
+PyCOLMAP can leverage the GPU for feature extraction, matching, and multi-view
+stereo if COLMAP was compiled with CUDA support. Similarly, PyCOLMAP can run
+Delaunay Triangulation if COLMAP was compiled with CGAL support. This requires
+to build the package from source and is not available with the PyPI wheels.
+
+All of the above steps are easily configurable with python dicts which are
+recursively merged into their respective defaults, for example:
+```python
+pycolmap.extract_features(database_path, image_dir, sift_options={"max_num_features": 512})
+# equivalent to
+ops = pycolmap.SiftExtractionOptions()
+ops.max_num_features = 512
+pycolmap.extract_features(database_path, image_dir, sift_options=ops)
+```
+
+To list available options and their default parameters:
+
+```python
+help(pycolmap.SiftExtractionOptions)
+```
+
+For another example of usage, see [`example.py`](./example.py) or
+[`hloc/reconstruction.py`](https://github.com/cvg/Hierarchical-Localization/blob/master/hloc/reconstruction.py).
+
+## Reconstruction object
+
+We can load and manipulate an existing COLMAP 3D reconstruction:
+
+```python
+import pycolmap
+reconstruction = pycolmap.Reconstruction("path/to/reconstruction/dir")
+print(reconstruction.summary())
+
+for image_id, image in reconstruction.images.items():
+    print(image_id, image)
+
+for point3D_id, point3D in reconstruction.points3D.items():
+    print(point3D_id, point3D)
+
+for camera_id, camera in reconstruction.cameras.items():
+    print(camera_id, camera)
+
+reconstruction.write("path/to/reconstruction/dir/")
+```
+
+The object API mirrors the COLMAP C++ library. The bindings support many other operations, for example:
+
+- projecting a 3D point into an image with arbitrary camera model:
+```python
+uv = camera.img_from_cam(image.cam_from_world * point3D.xyz)
+```
+
+- aligning two 3D reconstructions by their camera poses:
+```python
+rec2_from_rec1 = pycolmap.align_reconstructions_via_reprojections(reconstruction1, reconstrution2)
+reconstruction1.transform(rec2_from_rec1)
+print(rec2_from_rec1.scale, rec2_from_rec1.rotation, rec2_from_rec1.translation)
+```
+
+- exporting reconstructions to text, PLY, or other formats:
+```python
+reconstruction.write_text("path/to/new/reconstruction/dir/")  # text format
+reconstruction.export_PLY("rec.ply")  # PLY format
+```
+
+## Estimators
+
+We provide robust RANSAC-based estimators for absolute camera pose
+(single-camera and multi-camera-rig), essential matrix, fundamental matrix,
+homography, and two-view relative pose for calibrated cameras.
+
+All RANSAC and estimation parameters are exposed as objects that behave
+similarly as Python dataclasses. The RANSAC options are described in
+[`colmap/optim/ransac.h`](https://github.com/colmap/colmap/blob/main/src/colmap/optim/ransac.h#L43-L72)
+and their default values are:
+
+```python
+ransac_options = pycolmap.RANSACOptions(
+    max_error=4.0,  # for example the reprojection error in pixels
+    min_inlier_ratio=0.01,
+    confidence=0.9999,
+    min_num_trials=1000,
+    max_num_trials=100000,
+)
+```
+
+### Absolute pose estimation
+
+For instance, to estimate the absolute pose of a query camera given 2D-3D correspondences:
+```python
+# Parameters:
+# - points2D: Nx2 array; pixel coordinates
+# - points3D: Nx3 array; world coordinates
+# - camera: pycolmap.Camera
+# Optional parameters:
+# - estimation_options: dict or pycolmap.AbsolutePoseEstimationOptions
+# - refinement_options: dict or pycolmap.AbsolutePoseRefinementOptions
+answer = pycolmap.absolute_pose_estimation(points2D, points3D, camera)
+# Returns: dictionary of estimation outputs or None if failure
+```
+
+2D and 3D points are passed as Numpy arrays or lists. The options are defined in
+[`estimators/absolute_pose.cc`](./pycolmap/estimators/absolute_pose.h#L100-L122)
+and can be passed as regular (nested) Python dictionaries:
+
+```python
+pycolmap.absolute_pose_estimation(
+    points2D, points3D, camera,
+    estimation_options=dict(ransac=dict(max_error=12.0)),
+    refinement_options=dict(refine_focal_length=True),
+)
+```
+
+### Absolute Pose Refinement
+
+```python
+# Parameters:
+# - cam_from_world: pycolmap.Rigid3d, initial pose
+# - points2D: Nx2 array; pixel coordinates
+# - points3D: Nx3 array; world coordinates
+# - inlier_mask: array of N bool; inlier_mask[i] is true if correpondence i is an inlier
+# - camera: pycolmap.Camera
+# Optional parameters:
+# - refinement_options: dict or pycolmap.AbsolutePoseRefinementOptions
+answer = pycolmap.pose_refinement(cam_from_world, points2D, points3D, inlier_mask, camera)
+# Returns: dictionary of refinement outputs or None if failure
+```
+
+### Essential matrix estimation
+
+```python
+# Parameters:
+# - points1: Nx2 array; 2D pixel coordinates in image 1
+# - points2: Nx2 array; 2D pixel coordinates in image 2
+# - camera1: pycolmap.Camera of image 1
+# - camera2: pycolmap.Camera of image 2
+# Optional parameters:
+# - options: dict or pycolmap.RANSACOptions (default inlier threshold is 4px)
+answer = pycolmap.essential_matrix_estimation(points1, points2, camera1, camera2)
+# Returns: dictionary of estimation outputs or None if failure
+```
+
+### Fundamental matrix estimation
+
+```python
+answer = pycolmap.fundamental_matrix_estimation(
+    points1,
+    points2,
+    [options],       # optional dict or pycolmap.RANSACOptions
+)
+```
+
+### Homography estimation
+
+```python
+answer = pycolmap.homography_matrix_estimation(
+    points1,
+    points2,
+    [options],       # optional dict or pycolmap.RANSACOptions
+)
+```
+
+### Two-view geometry estimation
+
+COLMAP can also estimate a relative pose between two calibrated cameras by
+estimating both E and H and accounting for the degeneracies of each model.
+
+```python
+# Parameters:
+# - camera1: pycolmap.Camera of image 1
+# - points1: Nx2 array; 2D pixel coordinates in image 1
+# - camera2: pycolmap.Camera of image 2
+# - points2: Nx2 array; 2D pixel coordinates in image 2
+# Optional parameters:
+# - matches: Nx2 integer array; correspondences across images
+# - options: dict or pycolmap.TwoViewGeometryOptions
+answer = pycolmap.estimate_calibrated_two_view_geometry(camera1, points1, camera2, points2)
+# Returns: pycolmap.TwoViewGeometry
+```
+
+The `TwoViewGeometryOptions` control how each model is selected. The output
+structure contains the geometric model, inlier matches, the relative pose (if
+`options.compute_relative_pose=True`), and the type of camera configuration,
+which is an instance of the enum `pycolmap.TwoViewGeometryConfiguration`.
+
+### Camera argument
+
+Some estimators expect a COLMAP camera object, which can be created as follows:
+
+```python
+camera = pycolmap.Camera(
+    model=camera_model_name_or_id,
+    width=width,
+    height=height,
+    params=params,
+)
+```
+
+The different camera models and their extra parameters are defined in
+[`colmap/src/colmap/sensor/models.h`](https://github.com/colmap/colmap/blob/main/src/colmap/sensor/models.h).
+For example for a pinhole camera:
+
+```python
+camera = pycolmap.Camera(
+    model='SIMPLE_PINHOLE',
+    width=width,
+    height=height,
+    params=[focal_length, cx, cy],
+)
+```
+
+Alternatively, we can also pass a camera dictionary:
+
+```python
+camera_dict = {
+    'model': COLMAP_CAMERA_MODEL_NAME_OR_ID,
+    'width': IMAGE_WIDTH,
+    'height': IMAGE_HEIGHT,
+    'params': EXTRA_CAMERA_PARAMETERS_LIST
+}
+```
+
+
+## SIFT feature extraction
+
+```python
+import numpy as np
+import pycolmap
+from PIL import Image, ImageOps
+
+# Input should be grayscale image with range [0, 1].
+img = Image.open('image.jpg').convert('RGB')
+img = ImageOps.grayscale(img)
+img = np.array(img).astype(np.float) / 255.
+
+# Optional parameters:
+# - options: dict or pycolmap.SiftExtractionOptions
+# - device: default pycolmap.Device.auto uses the GPU if available
+sift = pycolmap.Sift()
+
+# Parameters:
+# - image: HxW float array
+keypoints, descriptors = sift.extract(img)
+# Returns:
+# - keypoints: Nx4 array; format: x (j), y (i), scale, orientation
+# - descriptors: Nx128 array; L2-normalized descriptors
+```

pycolmap-3.10.dev0.dist-info/RECORD

@@ -0,0 +1,45 @@
+pycolmap.cp312-win_amd64.pyd,sha256=sT55yFsiwVTWAsiTfxQsaeJ7yg_8beQYB8UwWka79_M,7453184
+pycolmap-3.10.dev0.data/platlib/boost_filesystem-vc144-mt-x64-1_85-f067f9ed486db4834c0d1a7df3189e1b.dll,sha256=lJ8fgEKJsdZtVfmBE0noCli6RPLXIx0sBJaeGjhR67E,147456
+pycolmap-3.10.dev0.data/platlib/boost_program_options-vc144-mt-x64-1_85-2e1824dab5bd231d4fa282e398c0b648.dll,sha256=IEndFRURQy2ygPQuG6hl4hvMbW4Uc-H4tDSp0cEUyo8,344576
+pycolmap-3.10.dev0.data/platlib/ceres-61b28aeca8e223f3fbc47f58603f8e06.dll,sha256=GUDZKogoAd8V6tb11p2fAl0Wz0IICsr4XV9GGJgt8Fs,1317888
+pycolmap-3.10.dev0.data/platlib/deflate-03f5a9337e7b36f61977f33fda571878.dll,sha256=FmWM_IGXLjrgNzOOOlark0HcnclfAL3mhK9wVU1RdvE,86528
+pycolmap-3.10.dev0.data/platlib/FreeImage-c6f1252e798b14e2c78db7236b8e8ebd.dll,sha256=NYr3ShPNX5w8w4Pgo-NaT17sQGFMsFbYx3A3pdZQ7J0,949760
+pycolmap-3.10.dev0.data/platlib/gflags-42f790d2cf73751c43bc0ae5d6c35e27.dll,sha256=bghfaWCAq4PmXAobSRH2D4sjC_MxavPq-lVDp3_Xxj4,120832
+pycolmap-3.10.dev0.data/platlib/glog-f2c4c633c583af361fc08448f1b3cc9a.dll,sha256=77ps5fBGJdLij_fhqcbKZYkwc_2YehOr9jH-pcS9VCU,211456
+pycolmap-3.10.dev0.data/platlib/Iex-3_2-fdd207ecd2435fbefa8594cf6bac6e42.dll,sha256=ERVFrATcXJ0VACVrG-kfSYqYaGy-JkQ1MKx5fF5lOxQ,282112
+pycolmap-3.10.dev0.data/platlib/IlmThread-3_2-3f1e925f6300289f1b994536c64dcfdc.dll,sha256=UjUdBdVh6Fdj3ohOALlnC6iZ6mUvDqfw_5n87jqDnyo,45568
+pycolmap-3.10.dev0.data/platlib/Imath-3_1-e5348926bce7468ef9a0b81cc3e90289.dll,sha256=pNKbLPqYgTSiuBu_WUcqYWho8m6AjKhzut7BT5_fzH0,337408
+pycolmap-3.10.dev0.data/platlib/jpeg62-8b57b7594d3b7aa46293dff855de275e.dll,sha256=QILNBL_hxWO9lTYa3iJbT_y51syDBa3p_1lgRoEkuAQ,678912
+pycolmap-3.10.dev0.data/platlib/lcms2-a36c7d906a2afd5a0d351950441031f6.dll,sha256=MtGqFtRAUoYz2LpTBeWaYBBtZ5HO85c2gdN1kuBWttk,358912
+pycolmap-3.10.dev0.data/platlib/libamd-d9d0a4400d3207d3e686fcb08b5d818c.dll,sha256=fZO7ms4xg2cbn5FDnh4jDpGDkZGlegZg-yUI2i0lB18,36864
+pycolmap-3.10.dev0.data/platlib/libcamd-54fce890c31ef057aad348e9ec072915.dll,sha256=svbwDoXEg3u_mRsf13auqAOOx1bTwmHqhmIUxZtKIQo,39936
+pycolmap-3.10.dev0.data/platlib/libccolamd-a6efb768968d8bf94d49343e7b7c8543.dll,sha256=2Z1E08Q_-ufhUz2CgrZrOG6TtasgCflkZjn7V4uscag,48128
+pycolmap-3.10.dev0.data/platlib/libcholmod-99fedc389f2f5ee569725faf598fb20c.dll,sha256=nKBqUaChs6hMnJ75aekN3aLKIwIH6DyVjTG6zuvqFYE,1212416
+pycolmap-3.10.dev0.data/platlib/libcolamd-8598768563f8a57d591be5e99c2f2def.dll,sha256=SbuMXYkuZRz2KcMbDdEVE8d21qNkO0wggNrtTTVZofo,32256
+pycolmap-3.10.dev0.data/platlib/libgcc_s_seh-1-1a6a3ffc779ffca2e2680f5ccce530de.dll,sha256=QsdIPxTWyaGVu3IDojo4NAG1cl1wTGWZcQJQ5agP0H4,150707
+pycolmap-3.10.dev0.data/platlib/libgfortran-5-1433bf2fc9362157088b7323782cd327.dll,sha256=rVjlurQxSY4Cqyyx3alktHVV-FziqFbxhjB4ecafK_4,3306867
+pycolmap-3.10.dev0.data/platlib/liblapack-33c5ae9de32ce90859555b5315faf319.dll,sha256=_MYd3UJhOWywPl60atMn-E0Lyu-X5DI1l_2E3G6mEX0,8110023
+pycolmap-3.10.dev0.data/platlib/liblzma-29fac5ea8a2444770a63b4eb277f11f9.dll,sha256=wO_Mpq1oSx9FS5x7ArlFM104YmnMvllCShBl36CM-Kk,187904
+pycolmap-3.10.dev0.data/platlib/libpng16-879680e3df35a6e0ebf408b2872cd379.dll,sha256=g0mMTAU5ePRToMuq8g2uowXNZ7EW7qZqbsQAby8THwk,202240
+pycolmap-3.10.dev0.data/platlib/libquadmath-0-f35ef621b617d5b1bedda957cd47034d.dll,sha256=t6eokUDTG1lu2-_jCCwNvF3mWVOMYAg95M8uBoGMHlc,380848
+pycolmap-3.10.dev0.data/platlib/libsharpyuv-33d9eb8be681f297d957c8edb481f7f7.dll,sha256=Zk9iCRarZeSTjor9KCUfawn-nirG8OKy4I4zbmBZSc0,26112
+pycolmap-3.10.dev0.data/platlib/libspqr-194c79ac68cd6679cbee93ffd3b150a3.dll,sha256=RE5JTP21mtjIGF7ntI09kqfev4DO_l5tgO9kuuHC1P4,184320
+pycolmap-3.10.dev0.data/platlib/libwebp-22c3769c12e027ed8afc4b004369236f.dll,sha256=T4WLzhIN_44NGfJHLbeTGm5JmVlXbI2g8vcwNEXCT68,373760
+pycolmap-3.10.dev0.data/platlib/libwebpdecoder-6625733bee7470ef2639a9eaf68b2467.dll,sha256=cTmxskjHTjZxyiLOA2F5WWJU6lBs3WBEkDVmw_vy_jM,162304
+pycolmap-3.10.dev0.data/platlib/libwebpmux-d5f10c74a5daa0455edeaa04d9e760b9.dll,sha256=MLqIgvVM49ao6AEufoDeb_PoEu2lTBoIcRbZYxQRilI,41472
+pycolmap-3.10.dev0.data/platlib/libwinpthread-1-747825cbaa4dbe2782431fcf59477996.dll,sha256=u8vl646AbzU3WF1MmDK07hX4ZhcyilZmldfTcoqjcO4,60798
+pycolmap-3.10.dev0.data/platlib/lz4-8ce5532d03be31aac2b216865b54f595.dll,sha256=LOOpIjCmQzT_o8mZ9bOd-fxfu1WEH0lG1W6poEHMaG8,121344
+pycolmap-3.10.dev0.data/platlib/msvcp140-5b69162e1e1ecdaec9dd8dc330c27ddc.dll,sha256=hUSON2360YWXQK7aolRLVl6Kbk4uVV3mxGOPSrGyiEM,621960
+pycolmap-3.10.dev0.data/platlib/openblas-67a685d4dacb64c4febd62528d7c249a.dll,sha256=1kowYk4VZw3kiEQxYAQzAMCuu7LDAFnYkCl57P8aKeY,1732096
+pycolmap-3.10.dev0.data/platlib/OpenEXR-3_2-2d0406abd803b529c46a80e0b50796b9.dll,sha256=bIuXMWsr4BTJyLvSDo8_A9Rl8K4dksNmHtJD1P5Do58,2906624
+pycolmap-3.10.dev0.data/platlib/OpenEXRCore-3_2-2d9a8f9061528eaea394d76b186ea571.dll,sha256=_0WPVHB0Ropk7IkagHL9lHKGdUbRx68XXZucFQVhTUA,2234880
+pycolmap-3.10.dev0.data/platlib/openjp2-102e352909272c529b59a3dc2f1844dd.dll,sha256=fBPUc5Hez3fAQqDAYLNzM_O8_BTuHNHDvwIe0lV1pL8,354816
+pycolmap-3.10.dev0.data/platlib/raw-1d39394d8615eca4aa3e700e86903fb3.dll,sha256=B0yJts228b9bGRc5pe41uq9tEnxEfAD683m4qr1yMZM,1117184
+pycolmap-3.10.dev0.data/platlib/sqlite3-ac1862382228bb4d89c7f3a84d337bd5.dll,sha256=4wgXn5MYu4h80OuRskPivoepEYf_ZOpn17-Jck7-jaE,1063424
+pycolmap-3.10.dev0.data/platlib/tiff-30c128b526ba84dcbca92a294af8f110.dll,sha256=2_WF-UbBhoBwtgqcduuZKxOW9WwCV3z00UwgHWslnL0,458752
+pycolmap-3.10.dev0.data/platlib/vcomp140-8a6328b999684c5720952a651c616fa4.dll,sha256=SLLP-kKlBkuime_xczdT9PoELZ1FLEnBHU-tJzYPeK4,192104
+pycolmap-3.10.dev0.data/platlib/zlib1-cb8d9f2cf9d19c9b37548c8033d77b9e.dll,sha256=_aGgBClMRUGvLJRk1oWcPMBblZCaL2iTZ9wk-6n3yUc,90624
+pycolmap-3.10.dev0.dist-info/DELVEWHEEL,sha256=_GQIik4abRQ8j0ln1-uK_R8P4RHGtYiMOtzgXaXRBbU,492
+pycolmap-3.10.dev0.dist-info/METADATA,sha256=1XlwMBCEmDAf6sTt-LgM-5CG-Y_MCqSfZswficB3Ius,10745
+pycolmap-3.10.dev0.dist-info/RECORD,,
+pycolmap-3.10.dev0.dist-info/WHEEL,sha256=raYSa41uyR3RTepDjt2zOjIhE3VDFqzbUhfN84nsytA,105

pycolmap-3.10.dev0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: scikit-build-core 0.9.8
+Root-Is-Purelib: false
+Tag: cp312-cp312-win_amd64
+