請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/16217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 | Yu-Ting Cheng | en |
| dc.contributor.author | 鄭宇婷 | zh_TW |
| dc.date.accessioned | 2021-06-07T18:05:28Z | - |
| dc.date.copyright | 2012-08-01 | |
| dc.date.issued | 2012 | |
| dc.date.submitted | 2012-07-25 | |
| dc.identifier.citation | [1] H. G. Barrow and J. M. Tenenbaum. Recovering intrinsic scene characteristics from
images. Technical Report 157, AI Center, SRI International, 333 Ravenswood Ave., Menlo Park, CA 94025, Apr 1978. [2] A. Bousseau, S. Paris, and F. Durand. User assisted intrinsic images. ACM Trans- actions on Graphics (Proceedings of SIGGRAPH Asia 2009), 28(5), 2009. [3] D. Comaniciu and P. Meer. Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24:603– 619, 2002. [4] Y. Dong, X. Tong, F. Pellacini, and B. Guo. Appgen: interactive material modeling from a single image. In Proceedings of the 2011 SIGGRAPH Asia Conference, SA ’11, pages 146:1–146:10, New York, NY, USA, 2011. ACM. [5] R. Grosse, M. K. Johnson, E. H. Adelson, and W. T. Freeman. Ground-truth dataset and baseline evaluations for intrinsic image algorithms. In International Conference 33on Computer Vision, pages 2335–2342, 2009. [6] E. Hsu, T. Mertens, S. Paris, S. Avidan, and F. Durand. Light mixture estimation for spatially varying white balance. ACM Trans. Graph., 27(3):70:1–70:7, Aug. 2008. [7] E. H. Land and J. J. McCann. Lightness and retinex theory. Journal of the Optical Society of America, 61:1–11, 1971. [8] I. Omer and M. Werman. Color lines: image specific color representation. In Pro- ceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition, CVPR’04, pages 946–953, Washington, DC, USA, 2004. IEEE Computer Society. [9] L. Shen, P. Tan, and S. Lin. Intrinsic image decomposition with non-local texture cues. In CVPR’08, pages –1–1, 2008. [10] L. Shen and C. Yeo. Intrinsic images decomposition using a local and global sparse representation of reflectance. In Proceedings of the 2011 IEEE Conference on Com- puter Vision and Pattern Recognition, CVPR ’11, pages 697–704, Washington, DC, USA, 2011. IEEE Computer Society. [11] M. F. Tappen, E. H. Adelson, and W. T. Freeman. Estimating intrinsic component images using non-linear regression. In Proceedings of the 2006 IEEE Computer 34Society Conference on Computer Vision and Pattern Recognition - Volume 2, CVPR ’06, pages 1992–1999, Washington, DC, USA, 2006. IEEE Computer Society. [12] M. F. Tappen, W. T. Freeman, and E. H. Adelson. Recovering intrinsic images from a single image. IEEE Trans. Pattern Anal. Mach. Intell., 27(9):1459–1472, Sept. 2005. [13] Y. Weiss. Deriving intrinsic images from image sequences. Computer Vision, IEEE International Conference on, 2:68, 2001. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/16217 | - |
| dc.description.abstract | 此論文探討關於物體本質影像之推測分析拆解問題。經過觀察，自然場景中的顏色可由少數種類的物質顏色來代表，我們透過取樣與投票機制重建出場景中的這些少數種類的代表色，並使用這群代表色的資訊，對物體本質的拆解提供全局稀疏及非局部的限制。
我們基於視網膜顏色感知理論以及擁有類似色彩的像素應有類似的物體本質色彩的假設，將物體本質影像之拆解問題用線性最小平方法來解決。以此方法所產生之本質影像能改進視網膜顏色感知理論的拆解結果，加上場景中的代表色資訊，對於影像編輯處理上具有很大的便利性。 | zh_TW |
| dc.description.abstract | This paper concerns about the intrinsic images decomposition problem, which is a long-standing ill-posed problem that targets the decomposition of an input image into shading and reflectance. Based on the observation that colors in the scene can be dominated by a representative set of material colors, we sample possible material colors in the scene and recover a set of dominant material colors through a voting scheme. With this set of material colors and the assumption that pixels with similar chroma should have similar reflectance, we adopt global sparsity and non-local constrains on reflectance and formulate the problem as a least square minimization problem. Our method improves Color Retinex algorithm and the intrinsic image decomposition results with the set of dominant material colors are friendly for many applications. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-07T18:05:28Z (GMT). No. of bitstreams: 1 ntu-101-R99944009-1.pdf: 16792429 bytes, checksum: a00e8bae3431ac7112892aea54bced39 (MD5) Previous issue date: 2012 | en |
| dc.description.tableofcontents | 口試委員會審定書 i
致謝 ii 中文摘要 iii Abstract iv 1 Introduction 1 2 Related work 3 2.1 Intrinsic Images 3 2.2 Reflectance Sparsity 5 3 Method 6 3.1 Image Formulation 6 3.2 Material Color Estimation 8 3.2.1 Segmentation 9 3.2.2 Voting Scheme 9 3.2.3 Set Estimation 10 3.3 Intrinsic Image Decomposition 11 3.3.1 Color Retinex 11 3.3.2 Reflectance Global Sparsity Constraint 12 3.3.3 KNN Non-local Constraint 13 3.3.4 Energy Function 14 4 Results and Applications 16 4.1 Evaluation on the Benchmark Dataset 16 4.2 Comparison with user-assisted approach 22 4.3 Applications 22 4.3.1 Reflectance Intensity Editing 23 4.3.2 Relighting 24 5 Conclusion 32 Bibliography 33 | |
| dc.language.iso | zh-TW | |
| dc.subject | 最小平方法 | zh_TW |
| dc.subject | 本質影像 | zh_TW |
| dc.subject | 物體本質與光影拆解 | zh_TW |
| dc.subject | 視網膜顏色感知理論 | zh_TW |
| dc.subject | 全局稀疏 | zh_TW |
| dc.subject | Least square minimization | en |
| dc.subject | Intrinsic Images | en |
| dc.subject | Reflectance-Illumination Separation | en |
| dc.subject | Retinex | en |
| dc.subject | Global sparse | en |
| dc.title | 非局部稀疏表示法之本質影像推測分析 | zh_TW |
| dc.title | Non-local Sparse Models for Intrinsic Images | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 100-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 李明穗,許秋婷,朱宏國 | |
| dc.subject.keyword | 本質影像,物體本質與光影拆解,視網膜顏色感知理論,全局稀疏,最小平方法, | zh_TW |
| dc.subject.keyword | Intrinsic Images,Reflectance-Illumination Separation,Retinex,Global sparse,Least square minimization, | en |
| dc.relation.page | 35 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2012-07-26 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-101-1.pdf 未授權公開取用 | 16.4 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。