本篇論文提出一個為 H.264/AVC 設計的低複雜度視訊高解析度重建方法。H.264/AVC 是一個受歡迎的視訊壓縮標準，其變動區塊的動作預測、動作補償與四分之一精度運動向量等特性，大幅減少了編碼冗餘，提升視訊壓縮率。本篇方法受益於由解碼器提供的視訊資訊，我們利用了位移預測模式、位移向量和動作補償冗餘的資訊，為不同的區塊制定合適的高解析度重建策略。對於含有較多細節的區域，我們進一步分為兩個類別進行不同策略的取樣提昇。與周圍鄰近區域相似的區塊，我們以其鄰近區塊加權後重建該高解析度區塊，其餘的則利用重建品質較佳的壓縮傳感技術來重建。在同質的區域，我們則採取較簡單的雙立方內插法重建高解析度的影像。其餘的區域，我們使用動作補償的方法重建，並且加上錯誤修正的處理。由於針對不同內容有調適性的重建方法，我們成功的減低了計算複雜度並且達到令人滿意的品質。由實驗結果可知，本論文的方法能有效率的對視訊資料做高解析度重建。同時本篇方法也有利於視訊資料在有限頻寬的網路中傳輸，並且具備發展的彈性。

A low-complexity video up-sampling for H.264/AVC algorithm is proposed in this thesis. H.264/AVC is a popular video coding standard. It utilizes variable block size for motion estimation and motion compensation, which results in better precision and coding efficiency. Our up-sampling processor benefits from the information given by the video decoder. We make use of the motion compensated prediction mode, motion vector and motion compensated residual to make appropriate policy for up-sampling image. For the areas with details, we further classify them to two categories. The areas with reconstructed similar neighboring patches are up-sampled by its weighted neighbors. Others are up-sampled by compress-sensing image super-resolution approach for good quality. The homogeneous areas are simply up-sampled via bicubic interpolation. And the remaining areas are reconstructed by motion compensation with error refinement. Due to the characteristic of content-adaptivity, we successfully reduce the computational complexity as well as achieve satisfactory quality. The experimental results demonstrate that the proposed method provides a more efficient way to up-sample video. Our approach is beneficial to video sharing through the internet with limited bandwidth.

[1] T. Wiegand, G. J. Sullivan, G. Bjøntegaard, and A. Luthra, “Overview of the H.264/AVC video coding standard, ” IEEE Transactions on Circuits and Systems for Video Technology, vol. 13, no. 7, pp. 560-576, July 2003.
[2] W. T. Freeman, T. R. Jones, and E. C. Paszor, “Example-based super-resolution,” IEEE Transactions on Computer Graphics and Applications, vol. 22, no. 2, pp. 55-65, 2002.
[3] W.T. Freeman, E.Pasztor, and O. Carmichael, “Learning low-level vision.” in Proc. Int. Conf. Computer Vision, vol. 2, 1999.
[4] M. F. Tappen, B. C. Russel, and W. T. Freeman, “Exploiting the sparse derivative prior for super-resolution and image demosaicing,” in Proc. IEEE Workshop Statistical and Computational Theories of Vision, 2003.
[5] Q. Shqn, Z. Li, J.Jia, and C. K. Tang, “Fast image/video upsampling,” ACM Trans. Graphics, vol. 27, no. 5, 2008.
[6] J. Sun, J. Sun, L. Quan, and H. Y. Shum, “Image super-resolution using gradient profile prior,” in IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[7] B. C. Song, S. C. Jeong and Y. Choi, “Video Super-resolution algorithm using bi-Derectional overlapped block motion compensation and on-the-fly dictionary training, ”IEEE Transactions on Circuits and Systems for Video Technology, vol. 21, no. 3, pp. 274-285, March 2011.
[8] J. Yang, J. Wright, T. Huang, and Y. Ma, “Image super-resolution as sparse representation of raw image patches,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2008.
[9] J. Yang, J. Wright, T. Huang and Y. Ma, “Image super-resolution via sparse representation,” IEEE Transactions on Image Processing, vol. 19, 2010.
[10] H. Chang, D. Yeung, and Y. Xiong, “Super-resolution through neighbor embedding”, in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp.275-282, 2004.
[11] Iain E. G. Richardson, “H.264 and MPEG-4 video compression,” The Robert Gordon University, Aberdeen, UK.
[12] Hervé Abdi, Lynne J., “Williams principal component analysis,” John Wiley & Sons, Inc., 2010.
[13] S. Farsiu, M. D. Robinson, M. Elad and P. Milanfar, “Fast and robust multiframe super resolution, ” IEEE Transactions on Image Processing, vol. 13, no. 10, pp. 1327-1344, October 2004.
[14] H. Takeda, P. Milanfar, M. Protter and M. Elad, “Super-resolution without explicit subpixel motion estimation, ” IEEE Transactions on Image Processing, vol. 18, no. 9, pp. 1958-1975, September 2009.
[15] C. Y. Yang, J. B. Huang and M. H. Yang, “Exploiting self-similarity for single frame super-resolution, ” in Proc. of the 10th Asian conference on Computer Vision, 2010.
[16] F. Brandi, R. Queiroz and D. Mukherjee, “Super-resolution of video using key frames and motion estimation,” in Proc. IEEE Int. Conf. Image Processing, pp. 321–324, Oct.2008.