Inverse Problems in Image Processing

(Main) Seminar: Inverse Problems in Image Processing

Leif Bergerhoff, Prof. Joachim Weickert

Summer Term 2019

(Main) Seminar (2 h)

Notice for bachelor/master students of mathematics: This is a »Hauptseminar« in the sense of these study programs.

Valgaerts et al., Joint estimation of motion, structure and geometry from stereo sequences.

NEWS:

2019/05/02: The write-up guidelines are online.

2019/02/07: Assigned topics (see Time Schedule) and the slides from the introductory meeting are online.

2019/02/06: Additional seminar literature is online (schedule adapted accordingly).

2019/02/05: Seminar literature and preliminary schedule are online.

2019/02/05: The registration period is over. There are still places left. Contact Leif Bergerhoff, if you are interested.

2019/01/31: Due to technical difficulties registrations before January 31 have not been processed correctly. Please fill out the registration form again if you registered for the seminar before this date. (see below)

2019/01/29: Registration for the seminar is open. (see below)

2019/01/23: Registration for the seminar is possible from Tuesday, January 29, 2019, 2 pm.

Important Dates – Description – Registration – Requirements – Introductory Meeting – Write-Up – Time Schedule – Literature

Introductory meeting (mandatory):
The introductory meeting will take place in building E1.7, room 4.10 on Thursday, Feburary 7, 2019, 4:15 p.m..
In this meeting, we will assign the topics to the participants. Attendance is mandatory for all participants. Do not forget to register first (see below).

Regular meetings during the summer term 2019:
Building E1.7, room 4.10 on Thursdays, 4:15 p.m.

Contents: Inverse problems form a very important class of mathematical problems and are ubiquitous in the field of image processing. Well-known examples are image deblurring, optic flow, inpainting, super-resolution, shape from shading, or 3d reconstruction. This seminar aims to provide an overview of fundamental techniques to solve inverse problems occuring in image processing. For this purpose, we discuss interesting scientific papers from recent conferences and journals as well as established concepts and methods.

Prerequisites: The seminar is for advanced bachelor or master students in Visual Computing, Mathematics, or Computer Science. Basic mathematical knowledge (e.g. Mathematik für Informatiker I-III) is required, and some knowledge in image analysis is recommended.

Language: All papers are written in English, and English is the language of presentation.

The registration period is over.

There are still places left. Contact Leif Bergerhoff, if you are interested.

Basic principle: Try to work on your topic as self-reliant as possible. If problems occur we expect from you that you try to find a solution on your own first. In the end it is your performance which we have to judge and we are not willing to do the main work for you. This does - however - not mean that you're not allowed to ask questions if you are still unclear about a certain thing. In this case we even encourage you to do so.

Regular attendance: You must attend all seminar meetings, except for provable important reasons (medical certificate).

Talk: Talk duration is 30 min, plus 15 min for discussion. Please do not deviate from this time schedule.
You may give a presentation using a data projector, overhead projector or blackboard, or mix these media appropriately. Your presentation must be delivered in English. Your slides and your write-up, too, have to be in English.

Opponent: Besides the main subject everyone gets assigned one more topic for which he or she takes over the role of an (active) opponent. This includes the preparation of meaningful questions as well as charing the session after the corresponding presentation.

Write-up: The write-up has to be handed in three weeks after the lecture period ends. The deadline is Friday, August 9, 2019, 23:59. The write-up should summarise your talk and has to consist of 5 pages per speaker. Electronic submission is preferred. File format for electronic submissions is PDF – text processor files (like .doc) are not acceptable. Do not forget to hand in your write-up: Participants who do not submit a write-up cannot obtain the certificate for the seminar.

Plagiarism: Adhere to the standards of scientific referencing and avoid plagiarism: Quotations and copied material (such as images) must be clearly marked as such, and a bibliography is required. Otherwise the seminar counts as failed.

Mandatory consultation: Talk preparation has to be presented to your seminar supervisor no later than one week before the talk is given. It is your responsibility to approach me timely and make your appointment.

No-shows: No-shows are unfair to your fellow students: Some talks are based on previous talks, and your seminar place might have prevented the participation of another student. Thus, in case you do not appear to your scheduled talk (except for reasons beyond your control), we reserve the right to exclude you from future seminars of our group.

Participation in discussions: The discussions after the presentations are a vital part of this seminar. This means that the audience (i.e. all participants) poses questions and tries to find positive and negative aspects of the proposed idea. This participation is part of your final grade.

Being in time: To avoid disturbing or interrupting the speaker, all participants have to be in the seminar room in time. Participants that turn out to be regularly late must expect a negative influence on their grade.

Please take a look at the slides from the introductory meeting.
Among others, they contain important information for preparing a good talk.

Please make sure to consider the write-up guidelines during the preparation of your final report.

We discuss the following research papers. If your registration was successful, the password for access will be sent to you before the first meeting.

1. Bergerhoff et al.:
   Modelling Stable Backward Diffusion and Repulsive Swarms with Convex Energies and Range Constraints.
   Energy Minimization Methods in Computer Vision and Pattern Recognition, October / November, 2017.
2. Bertalmío et al.:
   Navier-Stokes, Fluid Dynamics, and Image and Video Inpainting.
   Conference on Computer Vision and Pattern Recognition, December, 2001.
3. Buades et al.:
   A Non-Local Algorithm for Image Denoising.
   Conference on Computer Vision and Pattern Recognition, June, 2005.
4. Criminisi et al.:
   Region filling and object removal by exemplar-based image inpainting.
   IEEE Transactions on Image Processing, 13(9), 2004.
5. Han and Kan:
   Blind color-image deblurring based on color image gradients.
   Signal Processing, Volume 155, 2019.
6. Köser et al.:
   Dense 3D Reconstruction of Symmetric Scenes from a Single Image.
   Pattern Recognition, DAGM 2011.
7. Prados and Faugeras:
   Shape from Shading: A Well-Posed Problem?
   Conference on Computer Vision and Pattern Recognition, June, 2005.
8. Rudin et al.:
   Nonlinear total variation based noise removal algorithms.
   Physica D: Nonlinear Phenomena, Volume 60, Issues 1-4, 1992.
9. Valgaerts et al.:
   Joint Estimation of Motion, Structure and Geometry from Stereo Sequences.
   European Conference on Computer Vision, September, 2010.