Color-aware surface registration

Shuai Lin National University of Defense Technology, China Yu-Kun Lai Cardiff University, UK Ralph R. Martin Cardiff University, UK Shiyao Jin National University of Defense Technology, China Zhi-Quan Cheng Avatar Science Company, China

Geometric Modeling and Processing mathscidoc:1608.16083

Computers & Graphics, 58, 31-42, 2016.8
Shape registration is fundamental to 3D object acquisition; it is used to fuse scans from multiple views. Existing algorithms mainly utilize geometric information to determine alignment, but this typically results in noticeable misalignment of textures (i.e. surface colors) when using RGB-depth cameras. We address this problem using a novel approach to color-aware registration, which takes both color and geometry into consideration simultaneously. Color information is exploited throughout the pipeline to provide more effective sampling, correspondence and alignment, in particular for surfaces with detailed textures. Our method can furthermore tackle both rigid and non-rigid registration problems (arising, for example, due to small changes in the object during scanning, or camera distortions). We demonstrate that our approach produces significantly better results than previous methods.
Surface registration; Textures; Color aware; MeshHOG; Gabor filter
[ Download ] [ 2016-08-28 01:29:01 uploaded by yukunlai ] [ 388 downloads ] [ 0 comments ]
  title={Color-aware surface registration},
  author={Shuai Lin, Yu-Kun Lai, Ralph R. Martin, Shiyao Jin, and Zhi-Quan Cheng},
  booktitle={Computers & Graphics},
Shuai Lin, Yu-Kun Lai, Ralph R. Martin, Shiyao Jin, and Zhi-Quan Cheng. Color-aware surface registration. 2016. Vol. 58. In Computers & Graphics. pp.31-42.
Please log in for comment!
Contact us: | Copyright Reserved