Direkt zum InhaltDirekt zur SucheDirekt zur Navigation
▼ Zielgruppen ▼

Humboldt-Universität zu Berlin - Mathematisch-Naturwissenschaftliche Fakultät - Visual Computing

Dr. Anna Hilsmann

Image Hilsmann

  Phone +49-30-2093 3820 (HUB)
+49-30-31002 569 (HHI)
  Fax +49-30-2093 3168
  Email anna.hilsmann (at) informatik.hu-berlin.de
  Office 4.211 (Building 4, 2nd floor)
Johann von Neumann-Haus
Rudower Chaussee 25
12489 Berlin
  Mailing Address Humboldt-Universität zu Berlin
Institut für Informatik
Unter den Linden 6
10099 Berlin
Germany

 

I am a researcher in the Visual Computing Group at Humboldt University of Berlin. I also head the Computer Vision & Graphics Group at Fraunhofer HHI. See my homepage at Fraunhofer HHI for more detailed information.

 


Publications

Recent Publications see all publications

 

     P. Fechteler, A. Hilsmann, P. Eisert
"Example-based Body Model Optimization and Skinning", Eurographics 2016 Short Paper, Lisbon Portugal, May 2016.
 
     W. Paier, M. Kettern, A. Hilsmann, P. Eisert
"Video-based Facial Re-Animation", Proc. European Conference on Visual Media Production (CVMP 2015), London, UK, November 2015.
[pdf] [project page] [video]
 
     K. Ruhl, M. Eisemann, A. Hilsmann, P. Eisert, M. Magnor
"Interactive Scene Flow Editing for Improved Image-based Rendering and Virtual Spacetime Navigation", Proc. ACM Multimedia, Brisbane, Australia, October 2015.
[pdf] [bibtex] [video]
 
     M. Kettern, A. Hilsmann, P. Eisert
"Temporally Consistent Wide Baseline Facial Performance Capture via Image Warping", Vision, Modeling, and Visualization Workshop 2015, Aachen, Germany, October 2015.
[pdf] [bibtex] [video]
 
     M. Kettern, A. Hilsmann, P. Eisert
"Personalization of Statistical Face Models for Tracking and Realistic Animation", Joint Conference on Facial Analysis, Animation and Auditory-Visual Speech Processing, Vienna, Austria, September 2015.
[pdf] [bibtex]
 
ICIP2015.jpg      J. Furch, A. Hilsmann, P. Eisert
"A Framework for Image-Based Asset Generation and Animation", Proc. International Conference on Image Processing ICIP 2008, Québec City, Canada, 2015.
[pdf] [bibtex]
 
     A. Hilsmann, M. Stengel, L. Rogge
"Cloth Modeling", in Marcus Magnor and Oliver Grau and Olga Sorkine-Hornung and Christian Theobalt (Eds.): Digital Representations of the Real World: How to Capture, Model, and Render Visual Reality, CRC Press, ISBN 9781482243819, pp. 229-243,May 2015.
[url] [bibtex]
 
     C. Lipski, A. Hilsmann, C. Dachsbacher, M. Eisemann
"Image- and Video-based Rendering", in Marcus Magnor and Oliver Grau and Olga Sorkine-Hornung and Christian Theobalt (Eds.): Digital Representations of the Real World: How to Capture, Model, and Render Visual Reality, CRC Press, ISBN 9781482243819, pp. 261-280, May 2015
[url] [bibtex] .
 
     A. Hilsmann
"Image-based Approaches for Photo-Realistic Rendering of Complex Objects", Dissertation, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, March 2014.
[pdf]
 
     A. Hilsmann, P.Fechteler and P. Eisert
"Pose Space Image Based Rendering", Computer Graphics Forum 32(2) (Proc. of Eurographics 2013), May 2013.
[pdf] [bibitem] [Talk Slides] [project page]
 
Bild BMVC      A. Hilsmann, D.C. Schneider, P. Eisert
"Template-free Shape from Texture with Perspective Cameras", Proc. British Machine Vision Conference BMVC 2011, Dundee, Scotland, August 2011.
[pdf] [Short Abstract] [Talk Video] [Talk Slides] [bibitem]


Copyright Notice
All materials are presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors and other holders (publishers). These works may not be reposted without the explicit permission of the copyright holder.


Research

 

  
  
Pose-Space Image-based Rendering: Achieving real photorealism by physically simulating material properties and illumination is still computationally demanding and extremely difficult. Instead of relying on physical simulation, we follow a different approach for photo-realistic animation of complex objects, which we call Pose-Space Image-Based Rendering (PS-IBR).  more
  
Bild EG11a   
Near Regular Texture Analyis for Image-Based Texture Overlay: This work specifically addresses the decomposition of images of deformed regular textures into their intrinsic parts. These intrinsics decompose the image into the appearance of the undeformed regular texture, a deformation field, a shading map representing lighting effects and additional high frequency details. This is closely related to intrinsic image decomposition ... more
  
imgsft.jpg   
Template-Free Perspective Shape-from-Texture: We present a shape-from-texture SFT formulation, which is equivalent to a single-plane/multiple-view pose estimation problem statement under perspective projection. In contrast to the classical setting, we do not assume that a fronto-parallel view of the texture element is known a priori. Instead, we formulate the SFT problem akin to a Structure-from-Motion (SFM) problem, given n views of the same planar texture patch. ... more more
  
NRT Synthesis   
Near Regular Texture Synthesis: We developed a method to synthesize near-regular textures in a constrained random sampling approach. We treat the texture as regular and analyze the global regular structure of the input sample texture to estimate two translation vectors defining the size and shape of a texture tile. In a subsequent synthesis step, this structure is exploited to guide or constrain a random sampling process so that random samples of the input are introduced into the output preserving the regular structure previously detected... more
  
img_retexresearch.jpg   
Joint Estimation of Deformation and Photometric Parameters for Dynamic Texture Overlay: We developed a dynamic texture overlay method to augment non-rigid surfaces in single-view video. We are particularly interested in retexturing non-rigid surfaces, whose deformations are difficult to describe, such as the movement of cloth. Our approach is completely image-based and does not require any 3D reconstruction of the cloth surface... more
  
img_VM.jpg   
Virtual Clothing: We developed a virtual mirror prototype for clothes that uses a dynamic texture overlay method to change the color and a printed logo on a shirt while a user stands in front of the system wearing a prototype shirt with a (line)-pattern. Similar to looking into a mirror when trying on clothes, the same impression is created but for virtually textured garments. The mirror is replaced by a large display that shows the mirrored camera image... more

 


Short CV

Education
03/2014      Dr.-Ing. in Computer Science, Humboldt-Universität zu Berlin. Thesis: "Image-based Approaches for Photo-Realistic Rendering of Complex Objects"
10/2001-11/2006      Diploma in Electrical Engineering and Information Technology at RWTH Aachen University, Thesis: "Automatic Identification of Landmarks for Lung CT Registration", Institute of Imaging and Computer Vision, RWTH Aachen University , Philips Research Europe, Medical Image Processing
Work and Research Experience
since 01/2015      Head of Computer Vision & Graphics Group at Fraunhofer HHI
since 08/2011      Researcher in the Visual Computing Group at HU Berlin
04/2007-12/2014      Research Associate in the Computer Vision & Graphics Group at Fraunhofer HHI
04/2006-01/2007      Student Research Assistant/ Research Assistant, Philips Research Europe, Medical Image Processing
Awards
2015      VBKI Wissenschaftspreis
2011      Google Anita Borg Scholar
BMVC 2011 Student Bursary Recipient
Best Poster Award at Eurographics 2011
2009      Best Presentation Award, 2nd place, at the Vision, Modeling and Visualization Workshop 2009
2008      Best Paper Award of the CVPR 2008 NORDIA Workshop