计算机科学 ›› 2016, Vol. 43 ›› Issue (6): 321-324.doi: 10.11896/j.issn.1002-137X.2016.06.064
• 图形图像与模式识别 • 上一篇
杨琳,徐慧英,王艳洁
YANG Lin, XU Hui-ying and WANG Yan-jie
摘要： 在图像处理应用中,常常需要根据一些列相关的输入图片生成一张新的图片。现有的研究大都设定一些启发式规则用于图片的合成过程。为了提高图片合成的性能,提出了一种基于改进的贝叶斯方法的图片合成模型。在给定理想的图片合成模型后,对传感器误差和图片误差进行了分析。由于图片误差和几何误差之间是相关的,因此分析了它们之间的关系。在根据已有数据对模型进行后验估计时,通过最小化能量来得到模型的先验参数。在目标函数的优化过程中,基于现有研究通过重新赋权值的迭代方法进行优化问题的求解。最后,通过大量的实验表明,所提出的图片合成模型与相关方法相比具有更好的图片合成和渲染效果。
| [1] Kang S B,Li Y,Tong X,et al.Image-based rendering[J].Foundations and Trends in Computer Graphics and Vision,2012,2(3):173-258 [2] Dai Zhi-hua,Xu Yu-ping,Bu Jing,et al.Light Field Microscope to Achieve Three-Dimensional Real-Time Naked-Eye Display[J].ACTA OPTICA SINICA,2012,32(10):232-235(in Chinese) 戴志华,徐于萍,步敬,等.光场显微镜实现裸眼三维实时显示[J].光学学报,2012,32(10):232-235 [3] Liu Yong-chun,Gong Hua-jun,Shen Chun-ling,et al.Research of Lightfield Acquisition and Reconstruction Based on Mask[J].ACTA OPTICA SINICA,2014(8):105-110(in Chinese) 刘永春,龚华军,沈春林.基于掩膜的光场采集与重建的研究[J].光学学报,2014(8):105-110 [4] Buehler C,Bosse M,McMillan L,et al.Unstructured lumigraph rendering[C]∥Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques.ACM,2011:425-432 [5] Wanner S,Goldluecke B.Spatial and angular variational super-resolution of 4D light fields[M]∥Computer Vision-ECCV 2012.Springer Berlin Heidelberg,2012:608-621 [6] Baker S,Kanade T.Limits on super-resolution and how to break them[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,24(9):1167-1183 [7] Shan Q,Jia J,Agarwala A.High-quality motion deblurring from a single image[J].ACM Transactions on Graphics(TOG),ACM,2008,27(3):73-82 [8] Roth S,Black M J.Fields of experts:A framework for learning image priors[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005(CVPR 2005).IEEE,2005,2:860-867 [9] Chambolle A.An algorithm for total variation minimization and applications[J].Journal of Mathematical Imaging and Vision,2014,20(1/2):89-97 [10] Cho T S,Zitnick C L,Joshi N,et al.Image restoration by ma-tching gradient distributions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):683-694 [11] Beck A,Teboulle M.A fast iterative shrinkage-thresholding algorithm for linear inverse problems[J].SIAM Journal on Imaging Sciences,2009,2(1):183-202 [12] Wanner S,Meister S,Goldlücke B.Datasets and benchmarks for densely sampled 4D light fields[C]∥Annual Workshop on Vision,Modeling and Visualization:VMV.2013:225-226 [13] Vaish V,Adams A.The (New) Stanford Light Field Archive.http://lightfield.stanford.edu [14] Lin Xiao-ping,Zhou Shi-lin,Zhang Guan-liang,et al.An Image Mosaic Technology Based on Ant Colony Algorithm and Mutual Information Measure[J].Journal of Chongqing University of Technology(Natural Science),2013,7(1):76-81(in Chinese) 林小平,周石琳,张官亮,等.一种基于蚁群算法和互信息测度的图像拼接技术[J].重庆理工大学学报(自然科学),2013,7(1):76-81 |
| No related articles found! |
|
||
首页