Verica Lazova (PhD Student)

MSc Verica Lazova

Address
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Location
E1 4 - Room 609
Phone
+49 681 9325 2009
Fax
+49 681 9325 2099
Email
Get email via email

Personal Information

Research Interests

  • Human modeling from images
  • Generative models
  • Computer vision
  • Machine learning

Education

  • Ph.D. student, Perceiving and modelling people from video and images, Max-Planck-Institute for Informatics, Saarbrücken, Germany, (February 2019 - present)
  • M.Sc., Computer Science, International Max Planck Research School (IMPRS) and Saarland University, Saarbrücken, Germany, (October 2016 - February 2019)
  • B.Sc., Computer Science and Engeneering, Ss. Cyril and Methodius University, Skopje, Macedonia, (September 2011 - September 2015)

Other

http://virtualhumans.mpi-inf.mpg.de/people/Lazova.html

Publications

2019
Texture Completion of People in Diverse Clothing
V. Lazova
PhD Thesis, Universität des Saarlandes, 2019
360-Degree Textures of People in Clothing from a Single Image
V. Lazova, E. Insafutdinov and G. Pons-Moll
Technical Report, 2019
(arXiv: 1908.07117)
Abstract
In this paper we predict a full 3D avatar of a person from a single image. We infer texture and geometry in the UV-space of the SMPL model using an image-to-image translation method. Given partial texture and segmentation layout maps derived from the input view, our model predicts the complete segmentation map, the complete texture map, and a displacement map. The predicted maps can be applied to the SMPL model in order to naturally generalize to novel poses, shapes, and even new clothing. In order to learn our model in a common UV-space, we non-rigidly register the SMPL model to thousands of 3D scans, effectively encoding textures and geometries as images in correspondence. This turns a difficult 3D inference task into a simpler image-to-image translation one. Results on rendered scans of people and images from the DeepFashion dataset demonstrate that our method can reconstruct plausible 3D avatars from a single image. We further use our model to digitally change pose, shape, swap garments between people and edit clothing. To encourage research in this direction we will make the source code available for research purpose.