Hauptseminar: Advances in Image Processing and Computer Vision
Prof. Joachim Weickert,
Oliver Demetz
Winter Term 2013/2014
Seminar (2 h)
Notice for bachelor/master students of mathematics:
This is a »Hauptseminar« in the sense of these study programs.
|
tonemapped HDR reconstruction of a dynamic scene
[1].
|
Important Dates –
Description –
Registration –
Requirements –
Overview of Topics
Introductory meeting (mandatory):
Our introductory meeting took place on Wednesday, July 24, 2013, 16:15h, Building E1.7, Room 4.10.
The registration period is over.
Regular meetings during the winter term 2012/2013:
Tuesdays, 16:15h.
Building E1.7 Room 008
Date of first regular meeting:
Tuesday, October 29, 2013
Last meeting (planned):
Tuesday, January 14, 2014
Write-up submission deadline: February 28, 2014, 12:00h pm (midday)
Contents:
In this seminar, we want to discuss interesting scientific papers from
the field of image processing and computer vision. We will offer a
balanced mixture between recent conference or journal publications and
well-known, established concepts and methods.
The topics include but are not limited to image acquisition, image denoising
and inpainting, sparse data representation, computer vision, optic flow and
3-D reconstruction.
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.
You had to register for this course.
The registration period is over. You could register for this course
from Friday, July 19, 2013, 16:00h
to Tuesday, July 23, 2013, 15:15h.
Since the number of talks is limited, we ask for your understanding
that participants had to be considered strictly in the order of registration
– no exceptions.
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 should be delivered in English. Your slides and your
write-up, too, should be in English.
Write-up:
The write-up has to be handed until Friday, February 28, 2014 12:00h pm (midday).
The write-up should summarise your talk, about 5 pages per speaker
will be adequate in most cases.
Electronic submission is preferred. File format for electronic
submissions is PDF – text processor files (like .doc) are not acceptable.
Adhere to the standards of scientific referencing: Quotations and copied
material (such as images) must be clearly marked as such, and a bibliography
is required.
Do not forget to hand in your writeup, because participants that do not submit
a writeup cannot obtain the certificate for the seminar!
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 us timely and make your appointment!
No-shows:
In case you do not appear to your scheduled talk, we reserve the right to
exclude you from all 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 paricipants) 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.
We plan to discuss the following papers. If your registration was successful,
the password will be sent to you before the first meeting.
No. |
Date |
Speaker |
Paper |
Supervisor |
1 |
29.10.2013 |
Sinan Bozca |
Perona / Malik:
Scale Space and Edge Detection Using Anisotropic Diffusion.
Paper - Slides |
J. Weickert |
2 |
29.10.2013 |
Simon Heinzel |
Nordström:
Biased Anisotropic Diffusion -- a Unified Regularization
and Diffusion Approach to Edge Detection.
Paper - Slides |
J. Weickert |
3 |
05.11.2013 |
Giannis Kalofolias
|
Geman / Geman:
Stochastic Relaxation, Gibbs Distributions,
and the Bayesian Restoration of Images.
Paper - Slides |
J. Weickert |
4 |
05.11.2013 |
Hui Men
|
Ram / Elad / Cohen:
Image Processing using Smooth Ordering of its Patches
Paper - Slides |
O. Demetz |
5 |
12.11.2013 |
Alexander Scheer
|
Elad / Aharon:
Image Denoising Via Sparse and Redundant Representations Over Learned Sparse
Dictionaries
Paper - Slides |
O. Demetz |
6 |
12.11.2013 |
Lilli Kaufhold
|
Dabov / Foi / Katkovnik / Egiazarian:
Image denoising by sparse 3D transform-domain collaborative filtering
Paper - Slides |
O. Demetz |
7 |
19.11.2013 |
Chris Baumann
|
Frankot / Chellappa:
A Method for Enforcing Integrability in Shape from Shading
Algorithms.
Paper - Slides |
J. Weickert |
8 |
19.11.2013 |
Michél Biertz
|
Lowe:
Distinctive Image Features from Scale-Invariant Keypoints
Paper - Slides |
J. Weickert |
9 |
26.11.2013 |
Zornitsa Kostadinova
|
Zabih / Woodfill:
Non-parametric local transforms for computing visual correspondence
Paper - Slides |
O. Demetz |
10 |
26.11.2013 |
Mayur Bhamborae Jayaram
|
Gennert / Negahdaripour:
Relaxing the Brightness Constancy Assumption in Computing Optical Flow
Paper - Slides |
O. Demetz |
11 |
03.12.2013 |
Quynh Nguyen
|
Xu / Jia / Matsushita:
Motion Detail Preserving Optical Flow Estimation
Paper - Slides |
O. Demetz |
12 |
03.12.2013 |
Rajarshi Biswas
|
Chen / Jin / Lin / Cohen / Wu:
Large Displacement Optical Flow from Nearest Neighbor Fields
Paper - Slides |
O. Demetz |
13 |
10.12.2013 |
Banafsheh Sadry
|
Demetz / Hafner / Weickert:
The Complete Rank Transform: A Tool for Accurate and Morphologically
Invariant Matching of Structures
Paper - Slides |
O. Demetz |
14 |
10.12.2013 |
Özgün Cicek
|
Thirion:
Image Matching as a Diffusion Process:
an Analogy with Maxwell's Demons.
Paper - Slides |
J. Weickert |
15 |
17.12.2013 |
Christoph Michel
|
Kass / Witkin / Terzopoulos:
Snakes: Active Contour Models.
Paper - Slides |
J. Weickert |
16 |
17.12.2013 |
Sonja Forderer
|
Chan / Vese:
Active Contours Without Edges
Paper - Slides |
J. Weickert |
17 |
07.01.2014 |
Mykola Byelytskyy |
Grossberg / Nayar:
Modelling the Space of Camera Response Functions
Paper - Slides |
O. Demetz |
18 |
07.01.2014 |
Semih Korkmaz
|
Turk / Pentland:
Eigenfaces for Recognition
Paper - Slides |
J. Weickert |
19 |
14.01.2014 |
Constantin Berhard
|
Perez / Gangnet / Blake:
Poisson Image Editing.
Paper - Slides |
J. Weickert |
20 |
14.01.2014 |
Waqar Khan
|
P. Sen et al.:
Robust Patch-Based HDR Reconstruction of Dynamic Scenes
Paper - Slides |
O. Demetz |
-
Pradeep Sen, Nima Khademi Kalantari, Maziar Yaesoubi, Soheil Darabi,
Dan B Goldman and Eli Shechtman:
Robust Patch-Based HDR Reconstruction of Dynamic Scenes.
In ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia 2012),
Volume 31, No. 6, pages 1-11, 2012.
|