News

8 October 2015: Talk, Dr. Fang-Lue Zhang, Beijing

Title: Talk Structure-based image analysis and editing

Thursday, 8 October 2015, at 4 p.m.
Centre Universitaire d'Informatique, Battelle A, room 432 (3rd floor)

 

Fang-Lue Zhang is a post doctor in Visual Media Research Center in Tsinghua University, Beijing. He received his BS degree from the Zhejiang University in 2009 and Ph.D degree from Tsinghua University in 2015. His research interests include computer graphics, image processing and enhancement, image and video analysis and computer vision. He received IBM Excellent Research Fellowship in 2012 and National Award for Ph.D students from Tsinghua University in 2013. He is a member of ACM, IEEE and CCF.

Abstract:

As the most effective and direct forms of expression of visual information, image plays an important role in the modern society. With the rapid spread of consumer-grade media capture devices, ordinary users can even easily acquire stereo images and plenoptic images. This brings increased demands for intelligent processing techniques. To understand, analyze and recreate image content appropriately, we have to understand its regularities and intrinsic invariant properties. So we need to investigate how to utilize structural features of visual media data. In this talk, I will focus on structure-based image analysis and editing, and proposes several approaches to image representation, perceptual structure analysis and structure-preserving editing. I will also show applications in library-based interactive image editing, mixture creation of grouped elements, and plenoptic image editing based on layered structure.

References:

  • PatchTable: Efficient Patch Queries for Large Datasets and Applications
    Connelly Barnes 
    Fang-Lue Zhang , Liming Lou, Xian Wu, Shi-Min Hu
    ACM SIGGRAPH 2015
  •  
  • PatchNet: A Patch-based Image Representation for Interactive Library-driven Image Editing
    Shi-Min Hu*
    , Fang-Lue Zhang, Miao Wang, Ralph R. Martin and Jue Wang
    ACM SIGGRAPH Asia 2013
     
  • ImageAdmixture: Putting Together Dissimilar Objects from Groups
    Fang-Lue Zhang, Ming-Ming Cheng, Jiaya Jia, Shi-Min Hu*
    IEEE Transactions on Visualization and Computer Graphics (TVCG), 2012
     
  • Aesthetic Image Enhancement by Dependence-Aware Object Recomposition
  • Fang-Lue Zhang, Miao Wang, Shi-Min Hu*
  • IEEE Transactions on Multimedia (TMM), 2013
October 2, 2015
  News