全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

彩色图约束的二阶广义总变分深度图超分辨率重建

DOI: 10.11834/jig.20140807

Keywords: 深度图超分辨率重建,二阶广义总变分,边缘指示函数,TOF相机

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的针对深度图像分辨率非常低的问题,结合同场景高分辨率彩色图像,提出一种基于彩色图约束的二阶广义总变分深度图超分辨率重建方法。方法首先将低分辨率深度图映射到高分辨率彩色空间;然后利用二阶广义总变分模型,将带有边缘指示函数的高分辨率彩色约束项作为正则项,使得深度图像超分辨率重建问题变成最优求解问题;最后通过迭代重加权和原―对偶方法进行求解。结果实验结果表明,本文方法可以有效地保护图像的边缘结构,在定性和定量两个方面都可达到很好的效果。结论本文方法可以有效地解决深度图分辨率非常低的问题。

References

[1]  Lanman D, Taubin G. Build your own 3d scanner: 3d photography for beginners[C]// Proceedings of SIGGRAPH. New York, USA:ACM, 2009:1-87. [DOI:10.1145/1667239.1667247]
[2]  Kolb A, Barth E, Koch R, et al. Time-of-flight sensors in computer graphics[C]//Eurographics (State-of-the-Art Report). Munich, Germany:Eurographics, 2009:119-134. [DOI:10.1111/j.1467-8659.2009.01583. x]
[3]  Zhang X D, Wu G S, Hu L M, et al. Multi-view scattered point cloud optimization registration using a TOF camera[J]. Journal of Image and Graphics, 2013, 18(11):1445-1451. [张旭东, 吴国松, 胡良梅,等. 飞行时间3维相机的多视角散乱点云优化配准[J]. 中国图象图形学报, 2013, 18(11):1445-1451.][DOI:10.11834/jig.20131107]
[4]  Zhang X D, Shen Y L, Hu L M. Super-Resolution reconstruction algorithm for PMD range image based on regularization[C]// Proceedings of the International Conference on Intelligent Human Machine Systems and Cybernetics. Hangzhou, China: IEEE, 2011: 15-18.
[5]  Schuon S, Theobalt C, Davis J, et al. High-quality scanning using time-of-light depth super-resolution[C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Anchorage, USA:IEEE, 2008:1-7.
[6]  Rajagopalan A, Bhavsar A, Wallhoff F, et al. Resolution enhancement of PMD range maps[M]//Pattern Recognition. Berlin Heidelberg:Springer, 2008:304-313. [DOI:10.1007/978-3-540-69321-5_31]
[7]  Zhang X D, Shen Y L, Hu L M, et al. Improved super-resolution reconstruction algorithm for PMD range image[J]. Journal of Image and Graphics, 2012, 17(4):480-486. [张旭东, 沈玉亮, 胡良梅, 等. 改进的PMD距离图像超分辨率重建算法[J]. 中国图象图形学报, 2012, 17(4):480-486.][DOI:10.11834/jig.20120405]
[8]  Diebel J, Thrun S. An application of Markov random fields to range sensing[C]// Proceedings of Advances in Neural Information Processing Systems. Vancouver, Canada:MIT Press, 2005:291-298.
[9]  Yang Q, Yang R, Davis J, et al. Spatial-depth super resolution for range images[C]// Proceedings of Computer Vision and Pattern Recognition. Minneapolis, USA:IEEE, 2007:1-8. [DOI:10.1109/CVPR.2007.383211]
[10]  Cho J H, Ikehata S, Yoo H, et al. Depth map up-sampling using cost-volume filtering [C]// Proceedings of the 11th IEEE IVMSP Workshop. Seoul, Korea:IEEE, 2013:1-4. [DOI:10.1109/IVMSPW.2013.6611912]
[11]  Ferstl D, Reinbacher C, Ranftl R, et al. Image guided depth upsampling using anisotropic total generalized variation[C]// Proceedings of International Conference on Computer Vision. Sydney, Australia:IEEE, 2013: 993-1000.
[12]  Knoll F, Bredies K, Pock T. Second order total generalized variation for MRI[J]. Magnetic Resonance in Medicine, 2011, 65(2): 490-491. [DOI:10.1002/mrm.22595]
[13]  Bredies K, Kunisch K, Pock T. Total generalized variation[J]. SIAM Journal on Imaging Sciences, 2010, 3(3):492-526. [DOI: 10.1137/090769521]
[14]  Pock T, Zebedin L, Bischof H. TGV-fusion[M]//Rainbow of Computer Science. Berlin Heidelberg:Springer, 2011:245-258. [DOI:10.1007/978-3-642-19391-0_18]
[15]  Chambolle A, Pock T. A first-order primal-dual algorithm for convex problems with applications to imaging[J]. Journal of Mathematical Imaging and Vision, 2011, 40(1):120-145. [DOI:10.1007/s10851-010-0251-1]
[16]  Pock T, Chambolle A. Diagonal preconditioning for first order primal-dual algorithms in convex optimization[C]// Proceedings of International Conference on Computer Vision. Barcelona, Spain:ICCV, 2011:1762-1769. [DOI:10.1109/ICCV.2011.6126441]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133