-
-
Notifications
You must be signed in to change notification settings - Fork 850
CLI Parameters
aliceVision_cameraInit -> aliceVision_featureExtraction -> `aliceVision_imageMatching`_ -> `aliceVision_featureMatching`_ -> `aliceVision_incrementalSfM`_ -> `aliceVision_prepareDenseScene`_ -> aliceVision_depthMapEstimation -> aliceVision_depthMapFiltering -> `aliceVision_meshing`_ -> aliceVision_depthMapFiltering -> `aliceVision_texturing`_
A SfMData file (*.sfm) [if specified,--imageFolder cannot be used].
Input images folder [if specified, --input cannot be used].
Camera sensor width database path.
Output file path for the new SfMData file
Focal length in pixels. (or '-1' to unset)
Empirical value for the field of view in degree. (or '-1' to unset)
Intrinsics Kmatrix "f;0;ppx;0;f;ppy;0;0;1".
Camera model type (pinhole, radial1, radial3, brown, fisheye4, fisheye1).
When there is no serial number in the image metadata, we cannot know if the images come from the same camera. This is problematic for grouping images sharing the same internal camera settings and we have to decide on a fallback strategy:
- global: all images may come from a single device (make/model/focal will still be a differentiator).
- folder: different folders will be considered as different devices
- image: consider that each image has different internal camera parameters
Allow the program to process a single view.
Warning: if a single view is process, the output file can't be use in many other programs.
verbosity level (fatal, error, warning, info, debug, trace).
This program takes as input a media (image, image sequence, video) and a database (vocabulary tree, 3D scene data) and returns for each frame a pose estimation for the camera.
The sfm_data.json kind of file generated by AliceVision.
The folder path or the filename for the media to track
If a folder is provided it enables visual debug and saves all the debugging info in that folder
Filename for the SfMData export file (where camera poses will be stored).
Default : trackedcameras.abc.
Filename for the localization results (raw data) as .json
Folder containing the descriptors for all the images (ie the *.desc.)
The describer types to use for the matching
Preset for the feature extractor when localizing a new image {LOW,MEDIUM,NORMAL,HIGH,ULTRA}
The type of *sac framework to use for resection (acransac, loransac)
The type of *sac framework to use for matching (acransac, loransac)
Calibration file
Enable/Disable camera intrinsics refinement for each localized image
Maximum reprojection error (in pixels) allowed for resectioning. If set to 0 it lets the ACRansac select an optimal value.
[voctree] Number of images to retrieve in database
[voctree] For algorithm AllResults, it stops the image matching when this number of matched images is reached. If 0 it is ignored.
[voctree] Number of minimum images in which a point must be seen to be used in cluster tracking
[voctree] Filename for the vocabulary tree
[voctree] Filename for the vocabulary tree weights
[voctree] Algorithm type: FirstBest, AllResults
[voctree] Maximum matching error (in pixels) allowed for image matching with geometric verification. If set to 0 it lets the ACRansac select an optimal value.
[voctree] Number of previous frame of the sequence to use for matching (0 = Disable)
[voctree] Enable/Disable the robust matching between query and database images, all putative matches will be considered.
[bundle adjustment] If --refineIntrinsics is not set, this option allows to run a final global bundle adjustment to refine the scene
[bundle adjustment] It does not take into account distortion during the BA, it consider the distortion coefficients all equal to 0
[bundle adjustment] It does not refine intrinsics during BA
[bundle adjustment] Minimum number of observation that a point must have in order to be considered for bundle adjustment
SfMData file.
Output SfMData filename (.json, .bin, .xml, .ply, .baf, .abc).
-v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning, info, debug, trace).
SfMData file.
Output path for the features and descriptors files (*.feat, *.desc).
Path to folder(s) containing the extracted features.
Describer types used to describe an image:
- sift: Scale-invariant feature transform.
- sift_float: SIFT stored as float.
- sift_upright: SIFT with upright feature.
- akaze: A-KAZE with floating point descriptors.
- akaze_liop: A-KAZE with Local Intensity Order Pattern descriptors.
- akaze_mldb: A-KAZE with Modified-Local Difference Binary descriptors.
Path to folder(s) in which computed matches are stored.
verbosity level (fatal, error, warning, info, debug, trace).
Input folder containing the sift in float format.
Output folder that stores the sift in uchar format.
Perform a sanity check to check that the conversion and the generated files are the same.
verbosity level (fatal, error, warning, info, debug, trace).
SfMData file.
Path to the output Alembic file.
Describer types used to describe an image:
- sift: Scale-invariant feature transform.
- sift_float: SIFT stored as float.
- sift_upright: SIFT with upright feature.
- akaze: A-KAZE with floating point descriptors.
- akaze_liop: A-KAZE with Local Intensity Order Pattern descriptors.
- akaze_mldb: A-KAZE with Modified-Local Difference Binary descriptors.
image white list (uids or image paths).
Export views.
Export intrinsics.
Export extrinsics.
Export structure.
Export observations.
verbosity level (fatal, error, warning, info, debug, trace).
Estimate depth map for each input image.
SfMData file.
Images folder. Filename should be the image uid.
Output folder for generated depth maps.
Compute a sub-range of images from index rangeStart to rangeStart+rangeSize.
Compute a sub-range of N images (N=rangeSize).
Image downscale factor.
minimum angle between two views.
maximum angle between two views.
Semi Global Matching: Number of neighbour cameras.
Semi Global Matching: Size of the patch used to compute the similarity.
Semi Global Matching: GammaC threshold.
Semi Global Matching: GammaP threshold.
Refine: Number of neighbour cameras.
Refine: Number of samples.
Refine: Number of depths.
Refine: Number of iterations.
Refine: Size of the patch used to compute the similarity.
Refine: Sigma threshold.
Refine: GammaC threshold.
Refine: GammaP threshold.
Refine: Use current camera pixel size or minimum pixel size of neighbour cameras.
Export intermediate results from the SGM and Refine steps.
Number of GPUs to use (0 means use all GPUs).
verbosity level (fatal, error, warning, info, debug, trace).
Filter depth map to remove values that are not consistent with other depth maps.
SfMData file.
Input depth map folder.
Output folder for filtered depth maps.
Compute only a sub-range of images from index rangeStart to rangeStart+rangeSize.
Compute only a sub-range of N images (N=rangeSize).
minimum angle between two views.
maximum angle between two views.
Minimal number of consistent cameras to consider the pixel.
Minimal number of consistent cameras to consider the pixel when the similarity is weak or ambiguous.
Filter ball size (in px).
Filter ball size (in px) when the similarity is weak or ambiguous.
Number of nearest cameras.
verbosity level (fatal, error, warning, info, debug, trace).
SfMData file containing a complete SfM.
Output folder.
Export undistorted images for the animated camera(s). If false, animated camera(s) exported with original frame paths.
Path to the output SfMData file (with only views and poses).
Image file type: * .jpg * .png * .tif * .exr (half)
verbosity level (fatal, error, warning, info, debug, trace).
Export camera frustrums as a triangle PLY file
SfMData file.
PLY file to store the camera frustums as triangle meshes.
-v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning, info, debug, trace).
SfMData file.
Output path for keypoints.
Path to folder(s) containing the extracted features.
Describer types used to describe an image:
- sift: Scale-invariant feature transform.
- sift_float: SIFT stored as float.
- sift_upright: SIFT with upright feature.
- akaze: A-KAZE with floating point descriptors.
- akaze_liop: A-KAZE with Local Intensity Order Pattern descriptors.
- akaze_mldb: A-KAZE with Modified-Local Difference Binary descriptors.
verbosity level (fatal, error, warning, info, debug, trace).
SfMData file.
Output path for matches.
Path to folder(s) containing the extracted features.
Path to folder(s) in which computed matches are stored.
Describer types used to describe an image:
- sift: Scale-invariant feature transform.
- sift_float: SIFT stored as float.
- sift_upright: SIFT with upright feature.
- akaze: A-KAZE with floating point descriptors.
- akaze_liop: A-KAZE with Local Intensity Order Pattern descriptors.
- akaze_mldb: A-KAZE with Modified-Local Difference Binary descriptors.
verbosity level (fatal, error, warning, info, debug, trace).
Required parameters: -i [ --input ] arg SfMData file. -o [ --output ] arg Output folder.
Log parameters: -v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning,
info, debug, trace).
Required parameters: -i [ --input ] arg SfMData file. --ply arg Ply. -o [ --output ] arg Output folder.
Log parameters: -v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning,
info, debug, trace).
Required parameters: -i [ --input ] arg SfMData file. -o [ --output ] arg Output folder.
Log parameters: -v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning,
info, debug, trace).
Required parameters: -i [ --input ] arg SfMData file. -o [ --output ] arg Output folder.
Note: this program writes output in MVE file format
Log parameters: -v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning,
info, debug, trace).
aliceVision_exportMVSTexturing.exe AliceVision exportMVSTexturing:
Required parameters: -i [ --input ] arg SfMData file. -o [ --output ] arg Output folder.
Log parameters: -v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning,
info, debug, trace).
Required parameters: -i [ --input ] arg SfMData file. -o [ --output ] arg Output path for keypoints.
Optional parameters: --resolution arg (=1) Divide image coefficient --nbCore arg (=8) Nb core --useVisData arg (=1) Use visibility information.
Log parameters: -v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning,
info, debug, trace).
Required parameters: -i [ --input ] arg SfMData file. -o [ --output ] arg Output path for tracks. -f [ --featuresFolders ] arg Path to folder(s) containing the
extracted features.
- -m [ --matchesFolders ] arg Path to folder(s) in which computed
- matches are stored.
Optional parameters: -d [ --describerTypes ] arg (=sift) Describer types used to describe an
image: * sift: Scale-invariant feature transform. * sift_float: SIFT stored as float. * sift_upright: SIFT with upright feature. * akaze: A-KAZE with floating point descriptors. * akaze_liop: A-KAZE with Local Intensity Order Pattern descriptors. * akaze_mldb: A-KAZE with Modified-Local Difference Binary descriptors.
Log parameters: -v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning,
info, debug, trace).
Required parameters: -i [ --input ] arg SfMData file. -o [ --output ] arg Output path for the features and
descriptors files (*.feat, *.desc).
Optional parameters: -d [ --describerTypes ] arg (=sift) Describer types used to describe an
image: * sift: Scale-invariant feature transform. * sift_float: SIFT stored as float. * sift_upright: SIFT with upright feature. * akaze: A-KAZE with floating point descriptors. * akaze_liop: A-KAZE with Local Intensity Order Pattern descriptors. * akaze_mldb: A-KAZE with Modified-Local Difference Binary descriptors.
- -p [ --describerPreset ] arg (=normal)
- Control the ImageDescriber configuration (low, medium, normal, high, ultra). Configuration 'ultra' can take long time !
- --forceCpuExtraction arg (=0) Use only CPU feature extraction
- methods.
--rangeStart arg (=-1) Range image index start. --rangeSize arg (=1) Range size. --maxThreads arg (=0) Specifies the maximum number of threads
to run simultaneously (0 for automatic mode).
Log parameters: -v [ --verboseLevel ] arg (=info) verbosity level (fatal, error, warning,
info, debug, trace).