Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF D4 Publications :: Thesis :: Granados, Miguel


MPI-INF D4 Publications
Show all entries of:this year (2019)last year (2018)two years ago (2017)Open in Notes
Action:login to update  Library locked

Thesis - Doctoral dissertation | @PhdThesis | Doktorarbeit


Author
Author(s)*:Granados, Miguel
BibTeX citekey*:GranadosThesis2013
Language:English

Title, School
Title*:Advanced Editing Methods for Image and Video Sequences
School:Universität des Saarlandes
Type of Thesis*:Doctoral dissertation
Month:February
Year:2013


Note, Abstract, Copyright
LaTeX Abstract:In the context of image and video editing, this thesis proposes methods for modifying the semantic content of a recorded scene. Two different editing problems are approached: First, the removal of ghosting artifacts from high dynamic range (HDR) images recovered from exposure sequences, and second, the removal of objects from video sequences recorded with and without camera motion. These editings need to be performed in a way that the result looks plausible to humans, but without having to recover detailed models about the content of the scene, e.g. its geometry, reflectance, or illumination. The proposed editing methods add new key ingredients, such as camera noise models and global optimization frameworks, that help achieving results that surpass the capabilities of state-of-the-art methods. Using these ingredients, each proposed method defines local visual properties that approximate well the specific editing requirements of each task. These properties are then encoded into a energy function that, when globally minimized, produces the required editing results. The optimization of such energy functions corresponds to Bayesian inference problems that are solved efficiently using graph cuts. The proposed methods are demonstrated to outperform other state-of-the-art methods. Furthermore, they are demonstrated to work well on complex real-world scenarios that have not been previously addressed in the literature, i.e., highly cluttered scenes for HDR deghosting, and highly dynamic scenes and unconstrained camera motion for object removal from videos.
Keywords:video processing, image processing, combinatorial optimization, HDR deghosting, HDR reconstruction, video inpainting
Download Access Level:Public
Download File(s):View attachments here:

Referees, Status, Dates
1. Referee:Prof. Dr. Hans-Peter Seidel
2. Referee:Prof. Dr. Jan Kautz
Supervisor:Prof. Dr. Christian Theobalt
Status:Completed
First Lecture Title:Advanced Editing Methods for Image and Video Sequences
Location of Lecture:Campus E14, Room 019
Date Kolloquium:10 September 2013
Chair Kolloquium:Prof. Dr. Philipp Slusallek

Correlation
MPG Unit:Max-Planck-Institut für Informatik
MPG Subunit:Computer Graphics Group
MPG Subsubunit:Graphics, Vision and Video Group
Audience:experts only
Appearance:MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort

BibTeX Entry:

@PHDTHESIS{GranadosThesis2013,
AUTHOR = {Granados, Miguel},
TITLE = {Advanced Editing Methods for Image and Video Sequences},
SCHOOL = {Universit{\"a}t des Saarlandes},
YEAR = {2013},
TYPE = {Doctoral dissertation}
MONTH = {February},
}


Hide details for Attachment SectionAttachment Section

View attachments here:




Entry last modified by Miguel Andrés Granados Velásquez, 01/30/2014
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
[Library]
Created
09/18/2013 05:15:18 PM
Revision
1.
0.


Editor
Miguel Andrés Granados Velásquez
Miguel Andrés Granados Velásquez


Edit Date
09/18/2013 05:17:26 PM
09/18/2013 05:15:20 PM