ガラスなどの半透明物体への鏡面反射によって発生する映り込みは，カメラで被写体を撮影する際に頻繁に発生し問題となる．そのため様々な研究が行われているが， １枚の画像を背景成分と反射成分に分離することは不良設定問題となるため，精度よく分離することが困難となっている．本稿では，映り込み現象を畳み込みニューラルネットワークによって直接モデル化し，合成比や反射成分を学習に用いることで，効果的に学習を行うことが可能であることを示す．また先行研究では取り組まれてこなかった反射成分の推定にも挑戦し，背景成分と反射成分どちらにおいても先行研究を上回る精度で推定することが可能であることを示す．
[1] N. Arvanitopoulos, R. Achanta, and S. Su¨sstrunk. Single Image Reflection Suppression. Cvpr2017, (Ic):4498–4506, 2017.
[2] J. L. Barron, D. J. Fleet, and S. S. Beauchemin. Performance of optical flow techniques. International Journal of Computer Vision, 12(1):43–77, Feb 1994.
[3] J. Cheng, L. Dong, and M. Lapata. Long short-term memory-networks for machine reading. In EMNLP, pages 551–561, 2016.
[4] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2):303–338, June 2010.
[5] Q. Fan, J. Yang, G. Hua, B. Chen, and D. Wipf. A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing. aug 2017.
[6] X. Glorot, A. Bordes, and Y. Bengio. Deep sparse rectifier neural networks. AISTATS ’11: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, 15:315–323, 2011.
[7] J. Long, E. Shelhamer, and T. Darrell. Fully Convolutional Networks for Semantic Segmentation. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
[8] Y. Shih, D. Krishnan, F. Durand, and W. T. Freeman. Reflection removal using ghosting cues. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 07-12-June:3193–3201, 2015.
[9] Z. WANG. Image quality assessment : From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 2004.
[10] K. Wei, J. Yang, Y. Fu, W. David, and H. Huang. Single image reflection removal exploiting misaligned training data and network enhancements. In IEEE Conference on Computer Vision and Pattern Recognition, 2019.
[11] T. Xue, M. Rubinstein, C. Liu, and W. T. Freeman. A Computa- tional Approach for Obstruction-free Photography. ACM Trans. Graph., 34(4):79:1—-79:11, 2015.
[12] M. D. Zeiler. ADADELTA: an adaptive learning rate method. CoRR, abs/1212.5701, 2012.
[13] H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena. Self-attention generative adversarial networks, 2018.
[14] X. Zhang, R. Ng, and Q. Chen. Single image reflection separation with perceptual losses.
全国の大学の
卒論・修論・学位論文
を
一発検索！
論文の公開元へ