Saliency-aware Real-time Volumetric Fusion for Object Reconstruction

Sheng Yang Tsinghua University Kang Chen Tsinghua University Minghua Liu Tsinghua University Hongbo Fu City University of Hong Kong Shi-Min Hu Tsinghua University

Geometric Modeling and Processing mathscidoc:1708.16001

Computer Graphics Forum, 36, (7), 2017
We present a real-time approach for acquiring 3D objects with high fidelity using hand-held consumer-level RGB-D scanning devices. Existing real-time reconstruction methods typically do not take the point of interest into account, and thus might fail to produce clean reconstruction results of desired objects due to distracting objects or backgrounds. In addition, any changes in background during scanning, which can often occur in real scenarios, can easily break up the whole reconstruction process. To address these issues, we incorporate visual saliency into a traditional real-time volumetric fusion pipeline. Salient regions detected from RGB-D frames suggest user-intended objects, and by understanding user intentions our approach can put more emphasis on important targets, and meanwhile, eliminate disturbance of non-important objects. Experimental results on real world scans demonstrate that our system is capable of effectively acquiring geometric information of salient objects in cluttered real-world scenes, even if the backgrounds are changing.
Reconstruction, Object detection
[ Download ] [ 2017-08-08 22:58:54 uploaded by shimin ] [ 1005 downloads ] [ 0 comments ]
  • It's accepted paper by PG 2017, which will be published in Computer Graphics Forum
@inproceedings{sheng2017saliency-aware,
  title={Saliency-aware Real-time Volumetric Fusion for Object Reconstruction},
  author={Sheng Yang, Kang Chen, Minghua Liu, Hongbo Fu, and Shi-Min Hu},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20170808225855030503808},
  booktitle={Computer Graphics Forum},
  volume={36},
  number={7},
  year={2017},
}
Sheng Yang, Kang Chen, Minghua Liu, Hongbo Fu, and Shi-Min Hu. Saliency-aware Real-time Volumetric Fusion for Object Reconstruction. 2017. Vol. 36. In Computer Graphics Forum. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20170808225855030503808.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved