Seminar

Inpainting in Image Analysis

Winter Term 2024


Seminar: Inpainting: Foundations and Recent Advances

Dr. Pascal Peter, Kristina Schaefer

Winter Term 2024/25

Seminar (2 h)

Object removal. (Authors: Criminisi, Pérez, Toyama)


NEWS:

January 9, 2025:
The write-up template is online.

December 12, 2024:
Schedule is updated and slides are online.

July 15, 2024:
The website is online.



Important DatesDescriptionRegistrationRequirementsIntroductory MeetingOverview of Topics



Introductory meeting (mandatory):
Slides
Attendance is mandatory for all participants. Do not forget to register first (see below).

Regular meetings during the winter term 2024/25:
Wed 4-6 p.m., E.1.7 room 4.10.

LSF registration deadline:
TBA

Write-up submission deadline:
05.03.2025
LaTeX Template


Contents: Inpainting has been introduced as a technique to restore missing or deteriorated regions by using information from within the image. There are various ways to fill these missing parts such as comparing of image patches, diffusion-based methods or neural networks. Nowadays, specialised inpainting methods can remove objects seamlessly or can even reconstruct an image using only a tiny fraction of the original information. In this seminar, we cover both the foundations of the field as well as forefront research in the field of inpainting.

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), some knowledge in image processing and computer vision as well as basic knowledge in neural networks is required.

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


You must register for this course via the Seminar System .


We will discuss the following papers. All linked papers can be accessed for free, some of them require a VPN connection to Saarland university.


No. Date Speaker Topic
1 4.12. Can Wang M. Bertalmio, G. Sapiro, V. Caselles and C. Ballester:
Image inpainting

S. Masnou, J. Morel:
Level lines based disocclusion
(VPN required)

Slides
supervisor: Kristina Schaefer
2 4.12. Honglu Ma A. Criminisi, P. Pérez, and K. Toyama:
Region Filling and Object Removal by Exemplar-Based Image Inpainting
(VPN required)
Slides
supervisor: Kristina Schaefer
3 11.12. Pascal Peter C. Barnes, E. Shechtman, A. Finkelstein and D.B. Goldman:
PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing

Slides
4 11.12. Om Rajesh Khairate C. Schmaltz, P. Peter, M. Mainberger, F. Ebel, J. Weickert, and A. Bruhn:
Understanding, Optimising, and Extending Data Compression with Anisotropic Diffusion

Slides

supervisor: Pascal Peter
5 18.12. Sujatro Ghosh J. Xie, L. Xu and E. Chen:
Image Denoising and Inpainting with Deep Neural Networks

Slides

supervisor: Kristina Schaefer
6 18.12. Talha Khursheed Qazi J. Yu, J, Yang, X. Shen, X. Lu and T. Huang:
Generative Image Inpainting with Contextual Attention

Slides

supervisor: Pascal Peter
7 8.1. Hevra Petekkaya P. Peter:
A Wasserstein GAN for Joint Learning of Inpainting and Spatial Optimisation

supervisor: Pascal Peter
Slides
8 15.1. Pascal Peter J. Sohl-Dickstein, E. A. Weiss, N. Maheswaranathan, and S. Ganguli:
Deep Unsupervised Learning using Nonequilibrium Thermodynamics

Slides


MIA Group
©2001-2023
The author is not
responsible for
the content of
external pages.

Imprint - Data protection