אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב
דביר גינזבורג (אונ' תל-אביב)
יום שלישי, 28.12.2021, 11:30
Deep Point Correspondence presents a new method for real-time non-rigid dense correspondence between point clouds based on structured shape construction. The method requires a fraction of the training data compared to previous techniques and presents better generalization capabilities.
Until now, two main approaches have been suggested for the dense correspondence problem. The first is a spectral-based approach that obtains great results on synthetic datasets but requires mesh connectivity of the shapes and long inference processing time while being unstable in real-world scenarios. The second is a spatial approach that uses an encoder-decoder framework to regress an ordered point cloud for the matching alignment from an irregular input. Unfortunately, the decoder brings considerable disadvantages, as it requires a large amount of training data and struggles to generalize well in cross-dataset evaluations. DPC's novelty lies in its lack of a decoder component. Instead, we use latent similarity and the input coordinates themselves to construct the point cloud and determine correspondence, replacing the coordinate regression done by the decoder.
Dvir Ginzburg is a PhD candidate at Tel-Aviv University focusing on geometric deep learning.