Flower Reconstruction from a Single Photo

 Computer Graphics Forum(Proceedings of Eurographics 2014)

Feilong Yan 1      Minglun Gong 1,2      Daniel Cohen-Or 3      Oliver Deussen 4       Baoquan Chen 5,1   

1Shenzhen VisuCA/SIAT  2Memorial University of Newfoundland 3Tel Aviv University 4University of Konstanz  5Shandong University

Figure 1: Figure 1: A lily model is reconstructed from a single photo. From left to right: input photo, reconstructed mesh and textured models from the same view direction as the input, rendering result under a different direction.

We present a semi-automatic method for reconstructing flower models from a single photograph.  Such reconstruction is challenging since the 3D structure of a flower can appear ambiguous in projection. However, the flower head typically consists of petals embedded in 3D space that share similar shapes and form certain level of regular structure. Our technique employs these assumptions by first fitting a cone and subsequently a surface of revolution to the flower structure and then computing individual petal shapes from their projection in the photo. Flowers with multiple layers of petals are handled through processing different layers separately. Occlusions are dealt with both within and between petal layers. We show that our method allows users to quickly generate a variety of realistic 3D flowers from photographs and to animate an image using the underlying models reconstructed from our method.






Figure 2:Several results of reconstructed Flowers.

The authors would like to thank all the reviewers for their valuable comments. This work was partially supported by grants from NSFC (61379090, 61232011, 61272327), Guangdong Science and Technology Program (2011B050200007), Shenzhen Innovation Program (CXB201104220029A, KQCX20120807104901791, JCYJ20130401170306810,ZD201111080115A, KC2012JSJS0019A), CAS Visiting Professorship for Senior International Scientists, Natural Science and Engineering Research Council of Canada (293127) and the Israel Science Foundation.
  title = {Flower Reconstruction from a Single Photo},
  author = {Feilong Yan and Minglun Gong and Daniel Cohen-Or  and Oliver Deussen and Baoquan Chen}, 
  journal = {Computer Graphics Forum (Proceedings of Eurographics 2014)},
  volume = {33},
  number = {2},
  year = 2014

Copyright © 1998-2018 Visual Computing Research Center