Jan. 19, 2021, 2:04 p.m.

Master's thesis of Michał Stypułkowski "Representing Point Clouds with Generative Conditional Invertible Flow Networks" has won the first place in Master Thesis Competition in Applied Mathematics organized by BNY Mellon. The thesis has been prepared under supervision of Jan Chorowski. Currently, Michał is a PhD student in Institute of Computer Science, he teaches a class in Machine Learning for our data science students.
Michał Stypułkowski


Generative models for point clouds are believed to be a promising step towards intelligent systems able to generalize learned information about 3D objects. They are inspired by the human ability to perceive surroundings in terms of class-specific shape distributions.
“Representing Point Clouds with Generative Conditional Invertible Flow Networks” introduces a simple yet effective method to represent point clouds as sets of samples drawn from a cloud-specific probability distribution. More specifically, each cloud is represented as a parameterized probability distribution defined by a generative neural network. To exploit similarities between same-class objects and to improve model performance, weights are shared between the networks that model densities of points belonging to objects in the same family with the exception of a small, object-specific embedding vector.
As a result, the model offers competitive or superior quantitative results on benchmark datasets, while enabling unprecedented capabilities to perform cloud manipulation tasks, such as point cloud reconstruction and alignment.