Kategorie-Archiv: News


CSCS Speaker Announcement: Prof. Dr. Daniel Cremers

Prof. Dr. Daniel Cremers


Computer Vision for Autonomous Driving


Over the last years, the field of Computer Vision has matured from a fairly small niche area in computer science to one of the hottest topics in technological development today.  In my presentation, I will sketch a number of recent developments in computer vision and in particular in 3D reconstruction from moving cameras.  These methods for Simultaneous Localization and Mapping (SLAM) can accurately localize the camera and recover the observed 3D world.  They will form a central building block of future self-driving cars.


Prof. Dr. Daniel Cremers obtained a PhD in
Computer Science from the University of Mannheim, Germany.
Subsequently he spent two years as a postdoctoral researcher
at the University of California at Los Angeles (UCLA) and one year as
a permanent researcher at Siemens Corporate Research in Princeton,
NJ. From 2005 until 2009 he was associate professor at the University
of Bonn, Germany. Since 2009 he holds the chair for Computer Vision
and Pattern Recognition at the Technical University, Munich. His
publications received numerous awards, including the ‚Best Paper of
the Year 2003‘ (Int. Pattern Recognition Society), the ‚Olympus Award
2004‘ (German Soc. for Pattern Recognition) and the ‚2005 UCLA
Chancellor’s Award for Postdoctoral Research‘. For pioneering research
he received a Starting Grant (2009), a Proof of Concept Grant (2014)
and a Consolidator Grant (2015) by the European Research Council. In
December 2010 he was listed among „Germany’s top 40 researchers below
40“ (Capital). Prof. Cremers received the Gottfried-Wilhelm Leibniz
Award 2016, the most important research award in German academia.

ACM Chapters Computer Science in Cars Symposium 2017

>> Details about CSCS 2017 here.

CSCS Speaker Announcement: Prof. Dr. Michael Haller

Prof. Dr. Michael Haller

Prof. Dr. Michael Haller


Imperceptible Textile Interfaces in automotive use cases


Abstract: The increased interest in interactive soft materials, such as smart clothing and responsive surfaces, means that there is a need for flexible and deformable input devices.

We at the Media Interaction Lab are investigating the implementation and evaluation of next generation interfaces. In this presentation, we show how to implement curved, smart interfaces, ranging from printed film solutions to textile-based interfaces, which are then further used in different automotive use cases. These newly emerging form factors require novel human–computer interaction techniques which will be discussed in this presentation. In this work, we will further describe particular challenges and solutions for the design of flexible input sensors.


Michael Haller is a professor at the department of Interactive Media of the University of Applied Sciences Upper Austria (Hagenberg, Austria), where he is founder and director of the Media Interaction Lab (www.mi-lab.org), responsible for computer graphics & human-computer interaction. His core areas of expertise are smart graphics and interaction developing next-generation user interfaces. He received Dipl.-Ing. (1997), Dr. techn. (2001), and Habilitation (2007) degrees from Johannes Kepler University of Linz, Austria. His current focus is on innovative interaction techniques and smart interfaces for next generation working environments. Currently, he leads a team of over 10 researchers and students. He has been awarded the Erwin Schrödinger Fellowship Award, Google Research Award, Europrix Top Talent Award, Best ACM SIGGRAPH Emerging Technologies Award, and Microsoft Imagine Cup. Seven of his papers were awarded best paper or honorable mention at top HCI venues including ACM CHI and ACM UIST.

ACM Chapters Computer Science in Cars Symposium 2017

>> Details about CSCS 2017 here.

CSCS Speaker Announcement: Dr. Sudipta Bhattacharjee

Sudipta. 2

Dr. Sudipta Bhattacharjee (KPIT Technologies Ltd.)


Impact of quality of training dataset on pedestrian detection for autonomous driving


In autonomous driving, the perception task is a key piece requiring object detectors like pedestrian detection and vehicle detection among other. These object detectors are typically implemented using machine learning algorithms involving pipeline of classifiers or using deep learning networks. Special considerations are required for training dataset for each classifier in the pipeline. The performance of generated classifier models depends not just the size of the dataset but also the on quality of the training dataset in terms of coverage of scenarios. This work also presents the impact of ratio of positive and negative training samples sizes towards improving the performance of different types of classifiers in the pipeline.


Sudipta Bhattacharjee is Associate Solution Architect at the KPIT Technologies Ltd. for ADAS practice. He did his Ph. D. from Indian Institute of Technology, Kharagpur, India. He has more than 10 years of experience for conducting industrial R&D work. His areas of work includes computer vision techniques, machine learning, data analytics, wireless sensor network, electronic system design & integration. He has filed 5 patents, and published 1 book, 9 journals and 11 conference papers. He is the winner of scholarship A for 2014 ISRM International Symposium (ARMS8), Sapporo, Japan. He is the peer reviewer of IEEE transactions on industrial electronics, Journal of optics & lasers in engineering, IEEE sensor journal and IEEE wireless communication magazine.

ACM Chapters Computer Science in Cars Symposium 2017

>> Details about CSCS 2017 here.



CSCS Speaker Announcement: Dr. Mario Fritz


Dr. Mario Fritz (Max Planck Institute for Informatics)



Towards Anticipation in Traffic Scene Understanding


Scene understanding e.g. in terms of semantic segmentations and object detections has made great advances in recent years. In order to facilitate safe autonomous or assisted driving in real-world scene, we have to go beyond assessing the current traffic scene and rather predict possible consequences and future states.

I will present our latest work in this direction that aims at „predicting the future“. In particular, we have been developing Deep Learning techniques that encode prior observations and decode them in a recursive fashion and thereby extrapolate them into the future.


Mario Fritz is senior researcher at the Max Planck Institute for Informatics. He is heading a group on Scalable Learning and Perception. His research interest are centred around computer vision and machine learning but extend to natural language processing, robotics, graphics, HCI, privacy and more general challenges in AI. He did his postdoc at the International Computer Science Institute as well as UC Berkeley on a Feodor Lynen Research Fellowship of the Alexander von Humboldt Foundation. He received his PhD from TU Darmstadt and graduated from the University of Erlangen-Nuremberg.

ACM Chapters Computer Science in Cars Symposium 2017

>> Details about CSCS 2017 here.



CSCS Speaker Announcement: Dr. Alexey Dosovitskiy

Dr. Alexey Dosovitskiy

Dr. Alexey Dosovitskiy (Intel Visual Computing Lab)



Learning sensorimotor control from experience and demonstration


An intelligent agent should be capable of performing useful actions based on sensory observations – a feat known as sensorimotor control. The notion of usefulness depends on a specific situation – for instance, in a driving scenario useful actions would get the vehicle to the destination point as fast as possible without crashing or violating traffic rules. I will talk about two general approaches to learning sensorimotor control – learning from experience and learning from demonstration – and about recent research projects in our lab in both of these directions. In one, we train an agent to navigate in three-dimensional environments based purely on its experience, without any human supervision. In another, we use imitation learning to train an agent to drive in busy urban environments and follow passenger’s commands.


Alexey Dosovitskiy received his MSc and PhD degrees in mathematics (functional analysis) from Moscow State University in 2009 and 2012 respectively. He spent 2013-2015 as a postdoctoral researcher at the Computer Vision Group of Prof. Thomas Brox at the University of Freiburg in Germany, with research focus on deep learning, specifically unsupervised learning, image generation with neural networks, motion and 3D structure estimation. Since May 2016 Alexey works on deep learning and sensorimotor control at Intel Visual Computing Lab led by Dr. Vladlen Koltun.

ACM Chapters Computer Science in Cars Symposium 2017

>> Details about CSCS 2017 here.





ACM Chapters Computer Science in Cars Symposium 2017
Munich, Germany | July 6, 2017

>> Event Details

>> Get your Ticket here

Position Papers and Posters

We invite PhD and master students to submit position papers that will be compiled into proceedings of the event that will be available online on the Web pages. Each accepted position paper will be presented as a poster or might be selected for a short oral presentation. We plan also to invite the top ranked position papers and invited speakers to submit long papers for publication in a special issue of an international journal.

Submission information: Position papers should have the length of 2-4 pages in LNCS style formatting1. Please submit your position papers as PDF- file to the following email address:



  • Deadline for position papers:  June 6th, 2017

  • Notifications: June 14th, 2017

  • Event: July 6th, 2017


1 ftp://ftp.springer.de/pub/tex/latex/svproc/guidelines/Springer_Guidelines_for_Authors_of_Proceedings.pdf
(important downloads for authors)

Impressionen vom Event mit Paul Debevec und Mat Beck

Hier ein paar Eindrücke von unseren letzten Events mit Paul Debevec und Mat Beck, die wir mit euch teilen möchten: Bilder


Wir bedanken uns herzlich bei den Speakern und allen Teilnehmern-
von Vereinsmitgliedern und die, die es werden möchten, sowie bei bei allen Helfern die dieses spontane Event möglich gemacht haben.

Insbesondere gilt der Dank an Charlie Nedeltschev von Videocation für das Sponsoring der die Projektionstechnik, sowie an Lily Ivanova die die Speaker nach München gebracht hat!

Wir hatten eine schöne Zeit und freuen uns schon auf weitere Events dieses Jahr!

Euer Munich ACM SIGGRAPH Team

Update: Mat Beck, ASC kommt zum Event mit Paul Debevec



Mat Beck, ASC wird zu unserem morgigen Event einen Vortrag über „VFX for TV, Cinematography in new age“ halten.
Mat ist Visual Effects Supervisor, Producer, Cinematographer und Director,
bekannt für seine Arbeit in über 70 Filmen (z.B. Titanic, Spider-Man 2), mehreren TV Serien (Game of Thrones, True Detective) sowie in Werbung und Musikvideos.
Hier könnt ihr Euch dazu kostenlos Anmelden.

Wir freuen uns auf Euch!
Euer Munich ACM SIGGRAPH Chapter Team.

Event mit Paul Debevec und Mat Beck beim Munich ACM SIGGRAPH Chapter


Nachdem Paul Debevecs Besuch zu unserem Chapter-Opening bereits ein großer Erfolg war, freuen wir uns Euch mitteilen zu können, dass wir es auch in diesem Jahr wieder geschafft
haben ihn für einen Vortrag am Sonntag den 1. Mai in München gewinnen zu können.

Wir geben euch damit die Gelegenheit an seinem Vortrag „Practical Multispectral Lighting Reproduction“ teilzunehmen.
Er wird dabei neue Erkenntnisse der „Light Stage X“ preisgeben, mit der bereits viele High Resolution Facial Scans von Schauspielern erstellt wurden.
Hier die genaue Beschreibung seines Vortrags:

„This talk will present recent results using the Light Stage X system at the University of Southern California’s Institute for Creative Technologies in creating photoreal digital characters (such as Furious 7 and The Jungle Book), filming live-action so that lighting can be changed in postproduction, and in reproducing real-world lighting conditions within a studio including complex multispectral illuminants. Our latest multispectral lighting reproduction research to be presented at SIGGRAPH 2016 shows a practical method for recording HDRI maps of incident illumination including spectral information, and reproducing this illumination on multispectral Light Stage LEDs lights with six spectral channels.”

Paul ist Chief Visual Officer am Institute for Creative Technologies der USC in Pasadena/California und ist ein großer Förderer des Munich ACM SIGGRAPH Chapter.
Seine letzten Vorträge in München waren zum Thema Light Fields (2014 & 2015) sowie „Scanning the President of the United States“ in 2015 (zu finden auf unserem Vimeo Channel).

Im Anschluss wird Mat Beck, ASC einen Vortrag über
„VFX for TV, Cinematography in new age“ halten.
Mat ist Visual Effects Supervisor, Producer, Cinematographer und Director,
bekannt für seine Arbeit in über 70 Filmen (z.B. Titanic, Spider-Man 2), mehreren TV Serien (Game of Thrones, True Detective) sowie Werbung und Musikvideos.

Stattfinden wird das Event an der FWU am Bavariafilmplatz 3 um 13 Uhr,
Das Event ist kostenlos, eine Anmeldung ist hier erforderlich.

Wir freuen uns auf Euch!
Euer Munich ACM SIGGRAPH Chapter


13.15 – 13.30 Oliver Markowski: Begrüßung & Introduction
13.30 – 14.30 Paul Debevec: „Practical Multispectral Lighting Reproduction“
14.30 – 14.45 Pause // Networking
14.45 – 15.45 Mat Beck, ASC: VFX for TV, Cinematography in new age


SIGGRAPH (P)review – Impressionen

Vorab schon mal ein paar Impressionen von unserem SIGGRAPH (P)review: Bilder


An dieser Stelle nochmals ein kurzes Dankeschön an alle Beteiligten – insbesondere unseren Speakern Nils Thuerey, Benjamin Keinert und Michael Sänger, den zahlreichen Helfern, die für den reibungslosen Ablauf gesorgt haben, Andi Michl (three10) für die Projektionstechnik und Thomas „Huba“ Harbers (Geek’s home) für die technische Unterstützung…und nicht zuletzt unseren Gästen. Wir hoffen, dass es euch gefallen hat und freuen uns auf ein Wiedersehen! Nachtrag mit Infos zu den Talks und Encore Beiträgen folgt in Kürze als separater Post.