Across science, engineering, medicine and business we face a deluge of data coming from sensors, from simulations, or from the activities of myriads of individuals on the Internet. The data often has a geometric and/or visual character, as is the case with 1D GPS traces, 2D images and videos, 3D scans, and so on. Furthermore, the data sets we collect are frequently highly correlated, reflecting information about the same or similar entities in the world, or echoing semantically important repetitions/symmetries or hierarchical structures common to both man-made and natural objects. It is important to develop rigorous mathematical and computational tools for making such relationships or correspondences between data sets first-class citizens -- so that the relationships themselves become explicit, algebraic, storable and searchable objects. Networks of such relations can interconnect data sets into societies where the “wisdom of the collection” can be exploited in performing operations on individual data sets better, or in further assessing relationships between them. Examples include entity extraction from images or videos, 3D segmentation, the propagation of annotations and labels among images/videos/3D models, variability analysis in a collection of shapes, etc. The talk will cover general mathematical and computational tools for the construction, analysis, and exploitation of such relational networks -- illustrated by several concrete examples using 3D models and/or images. By creating societies of data sets and their associations in a globally consistent way, we enable a certain joint understanding of the data that provides the powers of abstraction, analogy, compression, error correction, and summarization. This ”functorial” view of geometric data puts the spotlight on consistent, shared relations and maps as the key to understanding structure in data. It is a little different from the current dominant paradigm of extracting supervised or unsupervised feature sets, defining distance or similarity metrics, and doing regression or classification – though sparsity still plays an important role. The inspiration is more from ideas in functional analysis and homological algebra, exploiting the algebraic structure of data relationships or maps in an effort to disentangle dependencies and assign importance to the vast web of all possible relationships among multiple geometric data sets. Ultimately, useful semantic structures simply emerge from these map networks. This is an overview of joint work with multiple collaborators, as discussed in the talk.

Presentation Slides

Image and Video Forensics through Content Analysis

James F. O'Brien
University of California, Berkeley

Advances in computational photography, computer vision, and computer graphics allow for the creation of visually compelling photographic forgeries. Forged images have appeared in tabloid magazines, main-stream media outlets, political attacks, scientific journals, and the hoaxes that land in our email in-boxes. These doctored photographs are appearing with growing frequency and sophistication, and even experts cannot rely on visual inspection to distinguish authentic images from forgeries. Techniques in image forensics operate on the assumption that photo-tampering will disturb some statistical or geometric property of an image. In a well-executed forgery these disturbances will either be perceptibly insignificant, or they may be noticeable but subjectively plausible. Methods for forensic analysis provide a means to detect and quantify specific types of tampering. To the extent that these perturbations can be quantified and detected, they can be used to objectively invalidate a photo. This talk will focus on forensic methods based on geometric content analysis. These methods work by finding inconsistencies in the geometric relationships among objects depicted in a photograph. The geometric relationships in the 2D image correspond to the projection of the relations that exist in the 3D scene. If a scene is known to contain a given relationship but the projected relation does not hold in the photograph, then one may conclude that the photograph is not a true projective image of the scene. The goal is to build a set of hard constraints that must be satisfied or else the image must be fake.

Presentation Slides

AN EVOLUTION OF MOBILE GRAPHICS, V2

Michael Shebanow
Samsung Research America

In this keynote, I’ll present my view on the evolution of Mobile Graphics, future directions for Mobile GPUs, and application directions. Mobile Graphics in this case refers to graphics devices embedded in handheld devices such as smart phones, phablets, and tablets. Due to the sheer volume of handheld devices shipped and because of the critical importance of graphics in such devices, a fiercely competitive market for Mobile GPUs has forced GPU designers to focus on continuous improvements in efficiency (limited power and limited cost structure) and device capabilities. Of course, this increased capability allows for exciting new applications in handheld devices of the future.

Presentation Slides

Paper Awards

Best Paper Award

Single-shot High Dynamic Range Imaging Using Coded Electronic Shutter by Hojin Cho, Seon Joo Kim, Seungyong Lee

Best Student Paper Award

Interactive Image-Guided Modeling of Extruded Shapes by Yan-Pei Cao, Tao Ju, Zhao Fu, Shi-Min Hu

Best Poster Award

Automatic 3D Posing from 2D Hand-Drawn Sketches by Alexandros Gouvatsos, Zhidong Xiao, Neil Marsden, Jian J. Zhang

Conference Photo Collection

Conference Photo Collection site : https://www.facebook.com/PG2014EWHA/photos