Computer Vision Seminar (Summer Term 2024)

Overview

Seminar (0/2/0) in GÖR/0127/U on Fridays, 9:20 - 10:50
Co-located with the Machine Learning Seminar. Talks are marked as belonging to one or the other seminar.
Lecturer: Bjoern Andres
Teaching Assistants: Jannik Irmai, David Stein, Holger Heidrich

Schedule

In this seminar, participating students will read, understand, prepare and present the contents of a research article or book chapter on a topic from the field of computer vision. The article or book chapter will be chosen by the student from the list below, or suggested by the student for approval in the beginning of the term. The preparation will include relevant foundational and related work. By attending at least seven presentations of their peers, students will get an overview of diverse topics in the field of computer vision.

Prerequisites

Prerequisites for taking this course are a solid foundational education in mathematics (esp. linear algebra and analysis) and theoretical computer science, as well as basics of machine learning and computer vision, comparable to the contents of the courses Machine Learning 1 and Computer Vision 1. For some of the suggested articles and book chapters, additional knowledge from the field of mathematical optimization is required.

Requirements

Requirements for passing this course are:

A 30-minute oral presentation by the student
A written report of about six pages to be submitted by the student before their presentation → Template with instructions
Active participation in at least seven presentations by other students
Additional forms of examination if required by the module toward which the course is to be credited

Suggested Research Articles

Segmentation

Ahmed Abbas, Paul Swoboda. RAMA: A Rapid Multicut Algorithm on GPU. CVPR 2022
Ahmed Abbas, Paul Swoboda. Combinatorial optimization for panoptic segmentation: A fully differentiable approach. NeurIPS 2021
Steffen Wolf, Alberto Bailoni, Constantin Pape, Nasim Rahaman, Anna Kreshuk, Ullrich Köthe, Fred A. Hamprecht. The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning. IEEE Transactions on Pattern Analysis and Machine Intelligence 43(10):3724-3738 (2021)
Kisuk Lee, Ran Lu, Kyle Luther, H. Sebastian Seung. Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction. IEEE Transactions on Medical Imaging 40(12):3801-3811 (2021)
Thorsten Beier, Constantin Pape, Nasim Rahaman, Timo Prange, Stuart Berg, Davi D. Bock, Albert Cardona, Graham W. Knott, Stephen M. Plaza, Louis K. Scheffer, Ullrich Koethe, Anna Kreshuk, Fred A Hamprecht. Multicut brings automated neurite segmentation closer to human performance. Nature Methods 14, 101–102 (2017).
Thorsten Beier, Fred A. Hamprecht, Jörg H. Kappes. Fusion moves for correlation clustering. CVPR 2015
Thorsten Beier, Thorben Kröger, Jörg H. Kappes, Ullrich Köthe, Fred A. Hamprecht. Cut, Glue, & Cut: A Fast, Approximate Solver for Multicut Partitioning. CVPR 2014

Tracking

Duy M. H. Nguyen, Roberto Henschel, Bodo Rosenhahn, Daniel Sonntag, Paul Swoboda. LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking. CVPR 2022
Andrea Hornáková, Timo Kaiser, Paul Swoboda, Michal Rolínek, Bodo Rosenhahn, Roberto Henschel. Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths. ICCV 2021
Andrea Hornáková, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda. Lifted Disjoint Paths with Application in Multiple Object Tracking. ICML 2020
Stefan Haller, Mangal Prakash, Lisa Hutschenreiter, Tobias Pietzsch, Carsten Rother, Florian Jug, Paul Swoboda, Bogdan Savchynskyy. A Primal-Dual Solver for Large-Scale Tracking-by-Assignment. AISTATS 2020

Matching

Tomás Dlask, Bogdan Savchynskyy. Relative-Interior Solution for (Incomplete) Linear Assignment Problem with Applications to Quadratic Assignment Problem. arXiv preprint 2023
Paul Roetzer, Paul Swoboda, Daniel Cremers, Florian Bernard. A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching. CVPR 2022
Lisa Hutschenreiter, Stefan Haller, Lorenz Feineis, Carsten Rother, Dagmar Kainmüller, Bogdan Savchynskyy. Fusion Moves for Graph Matching. ICCV 2021
Michal Rolínek, Paul Swoboda, Dominik Zietlow, Anselm Paulus, Vít Musil, Georg Martius. Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers. ECCV 2020

Deep Learning

Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer. High-Resolution Image Synthesis with Latent Diffusion Models. CVPR 2022
Özgün Çiçek, Ahmed Abdulkadir, S. Lienkamp, Thomas Brox, Olaf Ronneberger. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. MICCAI 2016