Consistent ZoomOut: Efficient Spectral Map Synchronization (SGP 2020)

views:58    added:2020-09-22 10:41    


Location:致真楼 801


In this talk, I will introduce a method called `Consistent ZoomOut' for efficiently refining correspondences among deformable 3D shape collections, while promoting the resulting map consistency. Our formulation is closely related to a recent unidirectional spectral refinement framework, but naturally integrates map consistency constraints into the refinement. Beyond that, our formulation can be adapted to recover the underlying isometry among near-isometric shape collections with a theoretical guarantee, which is absent in the other spectral map synchronization frameworks. In the end, I will demonstrate that our method improves the accuracy compared to the competing methods when synchronizing correspondences in both near-isometric and heterogeneous shape collections, but also significantly outperforms the baselines in terms of map consistency.

Short Bio:

Ruqi Huang is going to join TBSI as an assistant professor this fall. Prior to that, he obtained his PhD degree from the University of Paris-Saclay in 2016, and had been a postdoctoral researcher in Ecole Polytechnique from 2017 to 2019. Ruqi’s research interest lies in the areas of geometry processing, operator-based shape analysis, and 3D computer vision.

College of Computer Science and Software Engineering, Shenzhen University 2020