Deep Learning for Robust Normal Estimation in Unstructured Point Clouds
Please acknowledge our the reference paper :
"Deep Learning for Robust Normal Estimation in Unstructured Point Clouds " by Alexandre Boulch and Renaud Marlet, Symposium of Geometry Processing 2016, Computer Graphics Forum
Eigen and nanoflann (assumed to be in the source folder)
Torch
The code is NVIDIA GPU dependent.
Pretrained networks can be found at webpage. 3 models are proposed for download, 1, 3 and 5 scales (the models of the paper).
HoughCNN_Exec [options] -m path_to_the_torch_model -i input_file.xyz -c number_of_scales
Note: the input file must currently be at xyz format, it is possible to generate such file with Meshlab.
Note: the file predict.lua should be next to the executable.
Note: number of scales has to be consistent with the used model (there are separate models for different scales).
A file cube_100k is located in the test directory.
HoughCNN_Exec [options] -m path_to_the_torch_model -i test/cube_100k.xyz -c scale