direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Processing Digital Camera Images (WS10/11)

0433 L 370
Instructor:
Prof. Dr. Marc Alexa
Contact



Course structure:
Seminar - 2 SWS
Room:
E-N 719

Date:
Tuesday   4pm  -  6pm  
Start: 19 Oct 2010
End: 16 Feb 2011
Description:
Images taken with a digital camera can be processed and manipulated to create novel imagery unachievable with a single shot. In this course we will computationally create novel imagery by combining a large number of existing images, coming either from multiple shots of the same scene taken with varying camera parameters or from existing large image databases (e.g. Flickr). 
Additionally, we will explore state of the art methods for visualizing the results using natural user interfaces, e.g. multi-touch surfaces.
Requirements:
Interest in visual arts/photography, programming skills, ideally access to a digital camera (although this could be arranged for a limited number of participants).
Details:
The course gives a brief overview of the basic ideas and several recent developments in this field. Students will work in small teams on a chosen topic and present the basics of their topic in an intermediate talk. Finally, each team will implement a recent research paper and present their topic, application and results in a concluding talk. Both efficiency of the underlying algorithms as well as visual quality of the resulting imagery are important aspects in this course. Grading will be based on all aspects of performance.
Registration:
Please register for the course until October 19th by sending an eMail mentioning the course title, your name and student id to .

Slides

Das Dateilinks-Plugin steht nicht mehr zur Verfügung. Bitte verwenden Sie statt dessen das Plugin TUB Downloadliste.
Für die Löschung des alten Inhaltselements wenden Sie sich bitte an webmaster unter Nennung des Direktzugangs.

Schedule

  • 10/19/10: Intro
  • 10/26/10: Introduction/assignment of topics
  • 11/02/10: Talks

    • Gradient domain imaging: theory [slides]
    • Gradient domain imaging: applications [slides]

  • 11/09/10: Talks

    • Human visual system: eye [slides]
    • Human visual system: brain [slides shared with above]
    • Human visual system: dynamic range [slides]
    • Bilateral filter [slides]

  • 11/16/10: Talks

    • Image descriptors [slides]
    • GIST descriptor [slides shared with above]
    • Distance metrics [slides shared with above]
    • SIFT: keypoint detection [slides]
    • SIFT: feature extraction [slides]

  • 11/23/10: Talks

  • 11/30/10: Talks

    • Algorithms in current digital cameras [slides]
    • Cross Correlation
    • Noise in sensors [slides]

  • 12/07/10: Initial project presentations
  • 12/14/10: Discussion in class


Sample projects from previous courses

Generating an image with optimal depth of field from a series of images.
Lupe
Interactive Digital Photomontage: automatically combining a set of macro photographs yields an image that is sharp everywhere.
Lupe

Some samples of what students in previous classes implemented:

WS 09/10:



WS 08/09:

WS 07/08:


List of previous related courses:

Contact

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe