The CGV Colloquium will start online with a talk by Rana Hanocka (Tel Aviv University) on Friday, September 11 starting 16:00. The meeting is scheduled on Zoom, details are listed below.
Rana Hanocka is a 3rd-year PhD student in computer science at Tel Aviv University advised by Daniel Cohen-Or and Raja Giryes. At the intersection of Computer Graphics and Machine Learning, she is working on ways to use deep learning for manipulating, analyzing and understanding 3D shapes.
Title: Deep Learning on Single Shapes
One of the many difficulties in 3D deep learning is a lack of large, clean and labeled datasets. Acquiring and labeling large amounts of 3D data is not only cumbersome, but also requires using fundamental geometry processing pipelines that are not robust to geometry in the wild. Moreover, even high-quality 3D mesh models for similar shapes are extremely inconsistent with respect to triangulation and water-tightness, for example. On the other hand, training neural networks on single images has demonstrated surprisingly superb performance on a variety of different tasks. In this talk, I will present two recent works which propose training deep networks on a single shape. In Point2Mesh [SIGGRAPH 2020], we leverage the inductive bias of convolutional neural networks to learn a self-prior for surface reconstruction. We iteratively deform an initial mesh to “shrink-wrap” the input point cloud, resulting in a watertight mesh reconstruction. The weight-sharing property of CNNs models recurring and correlated structures within a single shape, and inherently removes noise and outliers. In Deep Geometric Texture Synthesis [SIGGRAPH 2020], we train a hierarchical GAN to learn to model the local geometric textures of a single shape. Our network displaces mesh vertices in any direction (i.e., in the normal and tangential direction), enabling synthesis of geometric textures, which cannot be expressed by a simple 2D displacement map.
All interested colleagues are more than welcome, so feel free to disseminate this announcement. As a reminder, all CGV MSc students (both seminar and thesis project) are expected to attend our monthly colloquium series.
You are cordially invited to attend our next Computer Graphics and Visualization (CGV) Colloquium, which will be held on Thursday March 21, 2013, 16:30-17.10, in the Vassiliadis Room (HB 10.230, formerly know as Shannon Room…)
The programme (this time, slightly shorter AND starting later) is as follows:
Timothy Kol, Remote rendering
Pedro Silva, Node-based shape grammar representation and editing
You are cordially invited to attend our next Computer Graphics and Visualization (CGV) Colloquium, which will be held on
Thursday February 21 2013, 15:45-17.00 in the new Vassiliadis Room (HB 10.230, formerly know as Shannon Room…)
The programme is as follows:
Joey van den Heuvel: Procedural ornamentation generation techniques
Casper van Leeuwen: Spatio-temporal 3D blood flow visualization in the human heart
Cees-Willem Hofstede: Digital anatomy representations
A discussion round on Wednesday 30th February was held in the TU Delft Science Center regarding the memorial of the North Sea Flood in 1953. 60 years ago, in the night of 31st January to the 1st February, a large flood hit the southern provinces of the Netherlands (Zeeland, South Holland and parts of Brabant). The flood took the inhabitants by in mid of the night by suprise, causing a death toll of several hundred people.
You are cordially invited to attend our first Computer Graphics and Visualization (CGV) Colloquium of 2013, which will be held on Thursday, January 17 at 15:45 in the Shannon Room, on the 10th floor of the EEMCS building.
The programme is as follows:
Hugo Meijer: Preprocessing large point-cloud data in the cloud
Chris van Egmond: Visualizing multiple two-dimensional data fields simultaneously in a single image
Because this is slightly shorter than usually, you are encouraged to make good use of that extra time, e.g. at the (by now traditional) socializing event following our colloquiums.