Volker Scholz

Research Area: computer graphics, image-based modeling Promotionskolloquium: May 21th, 2007 Ph.D. Thesis: New Editing Techniques for Video Post-Processing Contact:                               Max-Planck-Institut für Informatik Stuhlsatzenhausweg 85 D-66123 Saarbrücken Germany room: 423 phone: +49 681 9325-523 Fax: +49 681 9325-599

Informatik-Spektrum, Cover Image, April 2007

Projects:

	Editing Object Behavior in Video Sequences While there are various commercial-strength editing tools available today for still images, no comparable techniques yet exist for object-based manipulation of real-world video footage. In this paper, we present a framework for interactive video editing. Our framework is capable of removing and inserting objects, object motion editing, non-rigid object deformations, keyframe interpolation, as well as emulating camera motion.
	Texture Replacement of Garments in Monocular Video Sequences We present a video processing algorithm for texture replacement of moving garments in monocular video recordings as an extension of our multi-view capture method. A time-coherent texture interpolation is obtained by the use of 3D radial basis functions. Shading maps are determined with a surface reconstruction technique and applied to new textures which replace the color pattern in the video sequence.
	Garment Motion Capture Using Color-Coded Patterns We present a new image-based algorithm for surface reconstruction of moving garment from multiple calibrated video cameras. Using a color-coded cloth texture, we reliably match circular features between different camera views. The deforming geometry can be used for different graphics applications, e.g. for realistic retexturing.
	Cloth Motion from Optical Flow We have developed an algorithm for capturing the motion of deformable surfaces, in particular textured cloth. In a calibrated multi-view camera setup, we determine the optical flow between consecutive video frames and derive 3D vertex motion from optical flow. The resulting velocity field can cause distortions of the triangulated surface. We use a deformable surface model with constraints for vertex distances and curvature for smoothing and regularisation. Tracking errors in long video sequences are corrected by a silhouette matching procedure.

Talks:

• SIGGRAPH Sketch, 4 August 2005. PDF
  
• Eurographics paper, 1 September 2005.
• HiGraphics 2006
  

Publications:

• V. Scholz and M. Magnor, Texture Replacement of Garments in Monocular Video Sequences, Rendering Techniques 2006 (Proc. of the 17th Eurographics Symposium on Rendering EGSR 2006), Nicosia, Cyprus, pp. 305-312, June 2006. Final version available upon request. bibtex
  
• V. Scholz and M. Magnor, Multi-View Video Capture of Garment Motion, IEEE Workshop on Content Generation and Coding for 3D-Television, June 2006, Eindhoven, Netherlands.
  
• V. Scholz, T. Stich, M. Keckeisen, M. Wacker and M. Magnor, Garment Motion Capture Using Color-Coded Patterns, Computer Graphics Forum (special issue Eurographics 2005), vol. 24, no. 3, pp. 439-448, August 2005. bibtex
• V. Scholz and Marcus A. Magnor, Cloth Motion from Optical Flow, Proc. Vision, Modeling and Visualization 2004, Stanford, USA, pp. 117-124, November 2004. bibtex

Technical Reports:

• V. Scholz, Knowledge-based Locomotive Planning for the Swedish Railway,  Technical Report T2000-05, Swedish Institute of Computer Science (SICS), Stockholm, 2000. 
  
• V. Scholz and M. Magnor, Garment Texture Editing in Monocular Video Sequences based on Color-Coded Printing Patterns, MPI-I-2006-5-003, Max-Planck-Institut fuer Informatik, Saarbruecken, Germany.
  

Paper Reviewing:

• SIGGRAPH 2006
• EGSR 2006
  
• IEEE PAMI 2005, 2006
  
• Pacific Graphics 2005
• SCA 2005
• ICIP 2005, 2006
• BMVC 2006
  

CV:

• automatic tailor measurements on body scans (range scans)
• body scans with high-resolution texture
• animated body scans (BMBF project Virtual Try-On)