2 Hits in 2.6 sec

Handling Occlusion and Large Displacement Through Improved RGB-D Scene Flow Estimation

Yucheng Wang, Jian Zhang, Zicheng Liu, Qiang Wu, Philip A. Chou, Zhengyou Zhang, Yunde Jia
2016 IEEE transactions on circuits and systems for video technology (Print)  
An improved dense scene flow method based on RGB-D data is proposed in this paper.  ...  In the first stage, we propose a new RGB-D PatchMatch method, which is mainly applied in the RGB-D image space to reduce the computational complexity introduced by the large displacement motion.  ...  Scene flow on RGB-D image pairs Nici, Stefan and Largehand from [10] .  ... 
doi:10.1109/tcsvt.2015.2462011 fatcat:4dxu3bxb55h2fgvckb5lgwlbly

Multiframe Scene Flow with Piecewise Rigid Motion [article]

Vladislav Golyanik, Kihwan Kim, Robert Maier, Matthias Nießner, Didier Stricker, Jan Kautz
2017 arXiv   pre-print
We introduce a novel multiframe scene flow approach that jointly optimizes the consistency of the patch appearances and their local rigid motions from RGB-D image sequences.  ...  As a result, we obtain a qualitatively new level of accuracy in RGB-D based scene flow estimation which can potentially run in real-time.  ...  We believe that more improvements in RGB-D based scene flow estimation can be achieved within the proposed framework.  ... 
arXiv:1710.02124v1 fatcat:xdpzyjio2ra3jiy2fyh4acqbry