-
Notifications
You must be signed in to change notification settings - Fork 13
PatchMatchStereo
default: -1
Maximum image size in either dimension.
default: -1
Index of the GPU used for patch match. For multi-GPU usage, you should separate multiple GPU indices by comma, e.g. "0,1,2,3".
See: Multi-GPU support in dense reconstruction
default: -1
Minimum depth value. A lower bound of a range in which to randomly sample depth hypotheses.
default: -1
Maximum depth value. An upper bound of a range in which to randomly sample depth hypotheses.
default: 5
Half window size to compute NCC photo-consistency cost.
Window radius is to measure the size of a patch concerning how many surrounding pixels should contribute to the reconstruction around a focusing pixel.
default: 1
Number of pixels to skip when computing NCC. For a value of 1, every pixel is used to compute the NCC. For larger values, only every n-th row and column is used and the computation speed thereby increases roughly by a factor of window_step^2. Note that not all combinations of window sizes and steps produce nice results, especially if the step is greather than 2.
default: -1
Filter sigma in the coordinate space (standard deviation for range distance) for bilaterally weighted NCC. Larger values result in averaging of pixels with larger spatial differences.
default: 0.2
Filter sigma in the color space (standard deviation for radiometric similarity) for bilaterally weighted NCC. Larger values result in averaging of pixels with larger radiometric differences.
default: 15
Number of random samples to draw in Monte Carlo sampling.
default: 0.6
Spread of the NCC likelihood function.
default: 1
Minimum triangulation angle in degrees.
default: 0.9
Spread of the incident angle likelihood function.
default: 5
Number of coordinate descent iterations. Each iteration consists of four sweeps from left to right, top to bottom, and vice versa
default: 1 (enabled)
Whether to add a regularized geometric consistency term to the cost function. If true, the depth_maps and normal_maps must not be null.
default: 0.3
The relative weight of the geometric consistency term w.r.t. to the photo-consistency term.
default: 3
Maximum geometric consistency cost in terms of the forward-backward reprojection error in pixels.
default: 1 (enabled)
Whether to enable filtering.
default: 0.1
Minimum NCC coefficient for pixel to be photo-consistent.
default: 3
Minimum triangulation angle to be stable.
default: 2
Minimum number of source images have to be consistent for pixel not to be filtered.
default: 1
Maximum forward-backward reprojection error for pixel to be geometrically consistent.
default: 32
Cache size in gigabytes for patch match, which keeps the bitmaps, depth maps, and normal maps of this number of images in memory. A higher value leads to less disk access and faster computation, while a lower value leads to reduced memory usage. Note that a single image can consume a lot of memory, if the consistency graph is dense.
default: 0 (disabled)
Whether to tolerate missing images/maps in the problem setup.
default: 0 (disabled)
Whether to write the consistency graph.