請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/42064
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊永裕(Yung-Yu Chuang) | |
dc.contributor.author | Cheng-Da Chung | en |
dc.contributor.author | 鍾政達 | zh_TW |
dc.date.accessioned | 2021-06-15T00:44:43Z | - |
dc.date.available | 2011-08-19 | |
dc.date.copyright | 2011-08-19 | |
dc.date.issued | 2011 | |
dc.date.submitted | 2011-08-15 | |
dc.identifier.citation | [1] S. Avidan and A. Shamir. Seam carving for content-aware image resizing. ACM
Trans. Graph., 26(3):10, 2007. [2] T. Basha, Y. Moses, and S. Avidan. Geometric consistent stereo seam carving. In In Proc. ICCV, 2011. [3] R. Gal, O. Sorkine, and D. Cohen-Or. Feature-aware texturing. In Proceedings of Eurographics Symposium on Rendering, pages 297–303, 2006. [4] H. Hirschm¨uller. Accurate and efficient stereo processing by semi-global matching and mutual information. In In Proc. CVRP, pages 807–814. IEEE Computer Society, 2005. [5] H. Hirschm¨uller. Evaluation of cost functions for stereo matching. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007. [6] T. Igarashi and T. M. J. F. Hughes. As-rigid-as-possible shape manipulation. ACM Trans. Graph, 24:1134–1141, 2005. [7] F. Liu, M. Gleicher, H. Jin, and A. Agarwala. Content-preserving warps for 3d video stabilization. ACM Transcations on Graphics (Proceedings of ACM SIGGRAPH 2009), 28(3), 2009. [8] A. Mansfield, P. Gehler, L. V. Gool, and C. Rother. Scene carving: Scene consistent image retargeting. In European Conference on Computer Vision (ECCV), 09 2010. [9] Y. Niu, F. Liu, X. Li, and M. Gleicher. Warp propagation for video resizing. Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, 0:537–544, 2010. [10] C. Rother, V. Kolmogorov, and A. Blake. Grabcut: Interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics, 23:309–314, 2004. [11] A. Telea. An image inpainting technique based on the fast marching method. journal of graphics, gpu, and game tools, 9(1):23–34, 2004. [12] O. S. Yu-Shuen Wang, Chiew-Lan Tai and T.-Y. Lee. Optimized scale-and-stretch for image resizing. ACM Trans. Graph. (Proceedings of ACM SIGGRAPH ASIA, 27(5), 2008. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/42064 | - |
dc.description.abstract | 本論文提出了一立體圖像縮放法。傳統的圖像縮放法(Image Retargeting)試圖在縮放圖片比例的同時去維持畫面中重要物體的形狀。假若將左右兩眼的圖像獨立運用傳統的圖像縮放法處理,由於缺乏深度上的限制,必定會造成3D場景的破壞。人腦對於深度不連續處相當敏感。於是此篇論文所提出的立體圖像縮放法將輸入的左右眼圖像切成若干圖層,包括一個背景圖層和一個以上的前景圖層。此方法只在背景層上做形變(Warpping),並試圖將形變所產生的扭曲隱藏在前景層之下。之後利用回合最佳化(iterative optimization)填補圖層組合後所留下的洞,並同時透過視差限制(disparity constraint)維持場景的深度。此方法不但能夠保持場景中可見物體的形狀,也能維持場景的深度,特別是在深度不連續處。使得立體圖像能在不同長寬比的立體播放器都能有很好的呈現。此外,此方法所產生的結果能夠產生物體間新的遮擋(occlusion),使得即使縮放比例很大也能有很好的結果。 | zh_TW |
dc.description.abstract | This paper presents a warping-based stereo image retargeting algorithm that not only maintains visual quality but also preserves depth information. Image retargeting algorithms adapt content of an image to arbitrary aspect ratios without distorting the important objects in the image. However, retargeting left and right images in the stereo pair with an image retargeting algorithm independently will inevitably distort the disparity field and make it impossible to view 3D structures of the scene. Human brains are very sensitive to depth edges in the scene. As a result, the proposed algorithm separates both images into several layers. Applying different warping on each layer and hide distortion under foreground layer when compositing. After layer compositing, remaining holes are filled through our novel technique extit{Filling by Pulling} iteratively. Meanwhile, depth quality is maintained by disparity constraints. The proposed algorithm preserves both important content and depth information, especially depth edges, and generates results that adapt to different stereoscopic displays. Moreover, our method creates object occlusions when resizing intensely, thus provides more convincing results. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T00:44:43Z (GMT). No. of bitstreams: 1 ntu-100-R98922057-1.pdf: 10696948 bytes, checksum: 17aa429eddf33bc50f83899e3e04eff8 (MD5) Previous issue date: 2011 | en |
dc.description.tableofcontents | 口試委員會審定書i
Acknowledgments iii 致謝v 中文摘要vii Abstract ix 1 Introduction 1 2 Related work 3 3 Method 7 3.1 Input and Pre-process . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 3.2 Problem Formulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.3 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4 Result 25 4.1 Data Set . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4.2 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 4.3 Comparison . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 5 Conclusion 31 Bibliography 35 | |
dc.language.iso | en | |
dc.title | 基於形變的回合最佳化立體圖像縮放法 | zh_TW |
dc.title | Warping-based Stereo Image Retargeting by Iterative Optimization | en |
dc.type | Thesis | |
dc.date.schoolyear | 99-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 賴祐吉(Yu-Chi Lai),葉正聖(Jeng-Sheng Yeh),歐陽明(Ming Ouhyoung) | |
dc.subject.keyword | 形變,立體圖像縮放法,視差,拉扯填補法,物體遮擋, | zh_TW |
dc.subject.keyword | Warping-based,Stereo image retargeting,Disparity,Filling by Pulling,Object occlusion, | en |
dc.relation.page | 36 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2011-08-15 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-100-1.pdf 目前未授權公開取用 | 10.45 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。