Organizing Committee
Abstract

Optimization appears in many computer vision and image processing problems such as image restoration (denoising, inpainting, compressed sensing), multi-view reconstruction, shape from X, object detection, image segmentation, optical flow, matching, and network training. While there are formulations allowing for global optimal optimization, e.g. using convex objectives or exact combinatorial algorithms, many problems in computer vision and image processing require efficient approximation methods.

Optimization methods that are widely used range from graph-based techniques and convex relaxations to greedy approaches (e.g. gradient descent). Each method has different efficiency and optimality guarantees. The goal of this workshop is a broad discussion of mathematical models (objectives and constraints) and robust efficient optimization methods (exact or approximate, discrete or continuous) addressing existing issues and advancing the state of the art.

Image for "Optimization Methods in Computer Vision and Image Processing"

Confirmed Speakers & Participants

  • Speaker
  • Poster Presenter
  • Attendee
  • Virtual Attendee

Workshop Schedule

Monday, April 29, 2019
TimeEventLocationMaterials
8:30 - 8:55am EDTRegistration - ICERM 121 South Main Street, Providence RI 0290311th Floor Collaborative Space 
8:55 - 9:00am EDTWelcome - ICERM Director11th Floor Lecture Hall 
9:00 - 9:45am EDTOn Combining CRF and CNN - Olga Veksler, University of Waterloo11th Floor Lecture Hall
10:00 - 10:30am EDTCoffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15am EDTComputing Rolling Shutter Camera Pose via Optimized Algebraic Geometry - Tomas Pajdla, Czech Technical University in Prague11th Floor Lecture Hall
11:30 - 12:15pm EDTSemidefinite Programming in Multiview Geometry - Rekha Thomas, University of Washington11th Floor Lecture Hall
12:30 - 2:30pm EDTBreak for Lunch / Free Time  
2:30 - 3:15pm EDTMin-Max affine approximants and sketches. - Michael Werman, The Hebrew University of Jerusalem11th Floor Lecture Hall
3:30 - 4:00pm EDTCoffee/Tea Break11th Floor Collaborative Space 
4:00 - 4:45pm EDTPoint-Line Minimal Problems in Complete Multi-View Visibility - Kathlén Kohn, ICERM11th Floor Lecture Hall
5:00 - 6:30pm EDTWelcome Reception11th Floor Collaborative Space 
Tuesday, April 30, 2019
TimeEventLocationMaterials
9:00 - 9:45am EDTComplexity of a quadratic penalty accelerated inexact proximal point method for solving linearly constrained nonconvex composite programs - Renato Monteiro, Georgia Tech11th Floor Lecture Hall
10:00 - 10:30am EDTCoffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15am EDTRotation Averaging and Strong Duality - Fredrik Kahl, Chalmers University of Technology11th Floor Lecture Hall
11:30 - 12:15pm EDTApproximate Message Passing Algorithms for High-dimensional Statistical Estimation in Image Processing - Cynthia Rush, Columbia University11th Floor Lecture Hall
12:30 - 2:30pm EDTBreak for Lunch / Free Time  
2:30 - 3:15pm EDTValued Constraint Satisfaction Problems - Vladimir Kolmogorov, IST Austria11th Floor Lecture Hall
3:30 - 4:00pm EDTCoffee/Tea Break11th Floor Collaborative Space 
4:00 - 4:45pm EDTTesting and correcting distributions over big domains - Ronitt Rubinfeld, Massachusetts Institute of Technology11th Floor Lecture Hall
Wednesday, May 1, 2019
TimeEventLocationMaterials
9:00 - 9:45am EDTOptimization for Robust Deep Learning - M. Pawan Kumar, University of Oxford11th Floor Lecture Hall
10:00 - 10:30am EDTCoffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15am EDTImage segmentation methods and the use of pairwise similarities in data mining and pattern recognition - Dorit Hochbaum, UC Berkeley11th Floor Lecture Hall
11:30 - 12:15pm EDTNon-Convex Relaxations for Rank Regularization - Carl Olsson, Chalmers University of Technology and Lund University11th Floor Lecture Hall
12:30 - 12:40pm EDTGroup Photo11th Floor Lecture Hall 
12:40 - 2:30pm EDTBreak for Lunch / Free Time  
2:30 - 4:00pm EDTOptimization Methods in Computer Vision and Image Processing Poster Session11th Floor Collaborative Space
Thursday, May 2, 2019
TimeEventLocationMaterials
9:00 - 9:45am EDTAdversarial Training and Robust Optimization - Yair Weiss, Hebrew University of Jerusalem11th Floor Lecture Hall
10:00 - 10:30am EDTCoffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15am EDTOptimizing Jaccard, Dice, and other measures for image segmentation - Matthew Blaschko, KU Leuven11th Floor Lecture Hall
11:30 - 12:15pm EDTQuantum Inspired Methods for Computer Vision - Davi Geiger, New York University11th Floor Lecture Hall
12:30 - 2:30pm EDTBreak for Lunch / Free Time  
2:30 - 3:15pm EDTDiversity Maximization over Large Data Sets - Sepideh Mahabadi, Toyota Technological Institute at Chicago11th Floor Lecture Hall
3:30 - 4:00pm EDTCoffee/Tea Break11th Floor Collaborative Space 
4:00 - 4:45pm EDTDirect estimation of texture models for image segmentation - Pedro Felzenszwalb, Brown University11th Floor Lecture Hall 
Friday, May 3, 2019
TimeEventLocationMaterials
9:00 - 9:45am EDTProjective Splitting Methods for Decomposing Convex Optimization Problems - Jonathan Eckstein, Rutgers University11th Floor Lecture Hall
10:00 - 10:30am EDTCoffee/Tea Break11th Floor Collaborative Space 
10:30 - 11:15am EDTOn variational methods in imaging sciences, and Hamilton-Jacobi equations - Jerome Darbon, Brown University11th Floor Lecture Hall
11:30 - 12:15pm EDTSegmentation without Full Supervision - Yuri Boykov, University of Waterloo11th Floor Lecture Hall 
12:30 - 2:30pm EDTBreak for Lunch / Free Time  
3:30 - 4:00pm EDTCoffee/Tea Break11th Floor Collaborative Space 

Associated Semester Workshops

Computer Vision
Image for "Computer Vision"
Algebraic Vision Research Cluster
Image for "Algebraic Vision Research Cluster"
Computational Imaging
Image for "Computational Imaging"
Introduction to the ANTs Ecosystem
Image for "Introduction to the ANTs Ecosystem"

Lecture Videos

Diversity Maximization over Large Data Sets

Sepideh Mahabadi
Toyota Technological Institute at Chicago (TTIC)
May 2, 2019

Valued Constraint Satisfaction Problems

Vladimir Kolmogorov
Institute of Science and Technology (IST)
April 30, 2019