Rising Stars 2020:

Rana Hanocka

PhD Candidate

Tel Aviv University, Israel


Areas of Interest

  • Artificial Intelligence
  • Graphics

Poster

Point2Mesh: A Self-Prior for Deformable Meshes

Abstract

In this paper, we introduce Point2Mesh, a technique for reconstructing a surface mesh from an input point cloud. Instead of explicitly specifying a prior that encodes the expected shape properties, the prior is defined automatically using the input point cloud, which we refer to as a self-prior. The self-prior encapsulates reoccurring geometric repetitions from a single shape within the weights of a deep neural network. We optimize the network weights to deform an initial mesh to shrink-wrap a single input point cloud. This explicitly considers the entire reconstructed shape, since shared local kernels are calculated to fit the overall object. The convolutional kernels are optimized globally across the entire shape, which inherently encourages local-scale geometric self-similarity across the shape surface. We show that shrink-wrapping a point cloud with a self-prior converges to a desirable solution; compared to a prescribed smoothness prior, which often becomes trapped in undesirable local minima. While the performance of traditional reconstruction approaches degrades in non-ideal conditions that are often present in real world scanning, i.e., unoriented normals, noise and missing (low density) parts, Point2Mesh is robust to non-ideal conditions. We demonstrate the performance of Point2Mesh on a large variety of shapes with varying complexity. See project page for more details: https://ranahanocka.github.io/point2mesh/

Bio

Rana Hanocka is a Ph.D. candidate at Tel Aviv University under the supervision of Daniel Cohen-Or and Raja Giryes. Rana obtained an M.Sc. in Electrical Engineering from Tel Aviv University and a B.Sc. in Electrical Engineering from Rensselaer Polytechnic Institute in Troy, NY. Rana is the recipient of the 2020 Dan David Prize in Artificial Intelligence. Rana's research interests include computer graphics and machine learning. She is working on ways to use deep learning for manipulating, analyzing and understanding 3D shapes. Rana has co-authored multiple publications in leading venues in computer graphics and computer vision (SIGGRAPH, CVPR, TOG) and co-organized the Israeli Deep Geometric Learning Workshop.

Personal home page