植基於內容感知濾波的深度影像放大法｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	曾聿齡 Yu-Ling Tseng
論文名稱：	植基於內容感知濾波的深度影像放大法 Fast and Effective Successive Content-aware Filtering-based Upsampling for Depth Maps
指導教授：	鍾國亮 Kuo-Liang Chung
口試委員:	蔡文祥 Wen-Hsiang Tsai 貝蘇章 Soo-Chang Pei 陳炤彰 Chao-Chang A. Chen 鍾國亮 Kuo-Liang Chung 李同益 Tong-Yee Lee
學位類別：	碩士 Master
系所名稱：	電資學院 - 資訊工程系 Department of Computer Science and Information Engineering
論文出版年：	2018
畢業學年度：	106
語文別：	英文
論文頁數：	31
中文關鍵詞：	深度圖、深度無合成誤差(D-NOSE) 、可逆式資料隱藏、品質表現、內容感知濾波、放大
外文關鍵詞：	Depth map, Depth no-synthesis-error (D-NOSE), Reversible data hiding, Quality performance, Content aware filtering, Upsampling
相關次數：	點閱：197 下載：1
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

3-D 影片在合成虛擬彩圖前，將低解析度深度圖放大到高解析度是一個必要的步驟。本篇論文提出一個三階段植基於內容感知濾波的放大深度圖方法。在所提方法中，第一階段使用深度複製方法重建平滑區中缺少的深度像素值，這有利於降低計算複雜度和提高準確性。第二階段使用深度無合成誤差 (D-NOSE) 查表法重建半平滑區中缺少的深度像素值，且重建的深度像素值在合成虛擬彩色像素時，不會產生任何位移誤差。第三階段使用結合自適應混合和三邊濾波器的方法重建非平滑區中缺少的深度像素值，且重建的深度像素可以有效地去除邊緣模糊和紋理複製偽影。並且，我們提出一個新穎的可逆式資料影藏方法，其不需要任何位置圖。透過典型的測試深度圖，實驗結果顯示本篇論文所提出的三階段基於內容感知濾波器的放大方法與現存的方法相比，本篇方法有顯著的品質改善。

Upsampling low resolution depth maps to high resolution maps is a necessary step before synthesizing virtual color maps for 3-D videos. In this thesis, without any training process, a fast and effective three-stage successive content-aware filtering-based (SCAF) method is proposed to upsample depth maps. The first stage of the proposed method reconstructs the missing depth pixels in the homogeneous regions by the proposed depth duplicate approach which benefits computational complexity reduction and accuracy. The second stage reconstructs the missing depth pixels in the the semi-homogeneous regions using a fast depth no-synthesis-error (D-NOSE) lookup table-based approach proposed in this study, and the reconstructed depth pixels do not cause any errors in the warped virtual color pixels. The third stage reconstructs the missing depth pixels in the non-homogeneous regions using a joint adaptive hybrid and trilateral filtering approach proposed in this study, and the reconstructed depth pixels can effectively remove edge blurring and texture copying artifacts. In addition, without any location map overhead, we propose a novel region-based reversible data hiding method. Based on sixteen typical test depth maps, thorough experiments have been carried out to demonstrate the substantial quality improvement and computational complexity reduction merits of the proposed method over the existing state-of-the-art methods.

教授推薦書 i
論文口試委員審定書 ii
中文摘要 iii
Abstract in English iv
誌謝 v
Contents vi
List of Figures viii
List of Tables ix
Introduction 1
1 Related Works and Motivation 1
2 Contributions 3
The Proposed Successive Content-aware Filtering-based Method: SCAF 5
1 First Stage: The Depth Duplicate Approach to Upsample Depth Pixels in Homogeneous Regions .5
1.1 The Proposed Depth Duplicate Approach 5
1.2 Accuracy Benefits of the Proposed Depth Duplicate Approach 7
2 Second Stage: The Depth No-synthesis-error (D-NOSE) Lookup Table-based Approach to Upsample Depth Pixels in Semi-homogeneous Regions 9
2.1 Preliminary of D-NOSE Model 9
2.2 The Proposed D-NOSE Lookup Table Approach 10
3 Third Stage: The Joint Adaptive Hybrid and Trilateral Filtering (AHTF) Approach to Upsample Depth Pixels in Non-homegeneous Regions 12
3.1 The Proposed Adaptive Hybrid Approach in the First Phase of AHTF 12
3.2 The Adaptive Hybrid-based Trilateral Filtering Approach in the Second Phase of AHTF 14
The Proposed Region-based Reversible Data Hiding for Depth Maps 15
1 Embedding process 15
2 Extraction process 16
Experimental Results 17
1 PSNR, SSIM, and CPSNR Quality Merits of Our SCAF Method 17
2 Quality and Embedding Capacity Merits of Our RDH Method 19
3 Visual Perception Merit 20
4 The Computational Reduction Merit 20
Conclusion 26
Appendix I: The Proof of Theorem 1 31
                                

[1] O. M. Aodha, N. D. Campbell, A. Nair, and G. J. Brostow, “Patch based synthesis for single depth image super-resolution,” IEEE European Conference on Computer Vision, pp. 71-84, 2012.
[2] D. Chan, H. Buisman, C. Theobalt, and S. Thrun, “A noise-aware ﬁlter for real-time depth upsampling,” in Proc. Workshop Multi-Camera Multi-Modal Sensor Fusion Algorithms, pp. 1-12, 2008.
[3] O. Choi and S. W. Jung, “A consensus-driven approach for structure and texture aware depth map upsampling,” IEEE Transactions on Image Processing, vol. 23, no. 8, pp. 3321-3335, Aug. 2014.
[4] K. L. Chung, W. J. Yang, and W. N. Yang, “Reversible data hiding for depth maps using the depth no-synthesis-error model,” Information Sciences, vol. 269, pp. 159-175, Jun. 2014.
[5] B. C. Dhara and B. Chanda, “Color image compression based on block truncation coding using pattern fitting principle,” Pattern Recognition, vol. 40, no. 9, pp. 2408-2417, Sep. 2007.
[6] J. Diebel and S. Thrun, “An application of Markov random fields to range sensing,” International Conference on Neural Information Processing Systems, pp. 291-298, Dec. 2005.
[7] C. Dong, C. C. Loy, K. He, and X. Tang, “Learning a deep convolutional network for image super-resolution,” in proc. European Conference on Computer Vision, pp. 184-199, 2014.
[8] C. Fehn, “Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV,” Proc. SPIE, vol. 5291, pp. 93-104, May 2004.
[9] C. Fehn, P. Kauff, M. Op de Beeck, F. Ernst, W. Ijsselsteijn, M. Pollefeys, L. Vangool, E. Ofek, and I. Sexton, “An evolutionary and optimised approach on 3D-TV,” Int. Broadcast Convention, Amsterdam, Netherlands, pp. 357-365. , Sep. 2002.
10] D. Ferstl, C. Reinbacher, R. Ranftl, M. Rüther, and H. Bischof, “Image guided depth upsampling using anisotropic total generalized variation,” IEEE International Conference on Computer Vision, pp. 993-1000, Dec. 2013.
[11] G. Gilboa, N. Sochen, and Y. Y. Zeevi, “Image enhancement and denoising by complex diffusion processes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp. 1020-1036, Aug. 2004.
[12] K. He, J. Sun, and X. Tang, “Guided image filtering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1397-1409, Jun. 2013.
[13] M. Hornacek, C. Rhemann, M. Gelautz, and C. Rother, “Depth super resolution by rigid body self-similarity in 3D,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1123-1130, Jun. 2013.
[14] K. L. Hua, K. L. Lo, and Y. C. F. Wang, “Extended guided filtering for depth map upsampling,” IEEE Multimedia Magazine, vol. 23, no. 2, pp. 72-83, Jun. 2016.
[15] J. B. Huang, A. Singh, and N. Ahuja, “Single image super-resolution from transformed self-exemplars,” in proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 5197-5206, Jul. 2015.
[16] S. W. Jung, “Enhancement of image and depth map using adaptive joint trilateral filter,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 23, no. 2, pp. 258-269, 2013.
[17] J. Kim, J. Lee, S. Han, D. Kim, J. Min, and C. Kim, “Trilateral filter construction for depth map upsampling,” IEEE IVMSP Workshop, pp. 1-4, Sep. 2013.
[18] Y. Konno, Y. Monno, D. Kiku, M. Tanaka, and M. Okutomi, “Intensity guided depth upsampling by residual interpolation,” JSME/RMD International Conference on Advanced Mechatronics, pp. 1-2, 2015.
[19] Y. Konno, M. Tanaka, M. Okutomi, Y. Yanagawa, K. Kinoshita, and M. Kawade, “Depth map upsampling by self-guided residual interpolation,” International Conference on Pattern Recognition, pp. 1394-1399, Dec. 2016.
[20] J. Kopf, M. F. Cohen, D. Lischinski, and M. Uyttendaele, “Joint bilateral upsampling,” ACM Transactions on Graphics, vol. 26, no. 3, Jul. 2007, Art. ID 96.
[21] K. H. Lo, K. L. Hua, and Y. C. F. Wang, “Depth map super-resolution via Markov random fields without texture-copying artifacts,” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1414-1418, 2013.
[22] K. H. Lo, Y. C. F. Wang, and K. L. Hua, “Joint trilateral filtering for depth map super-resolution,” in Proc. IEEE Visual Communications and Image Processing, pp. 1-6, Nov. 2013.
[23] K. H. Lo, Y. C. F. Wang, and K. L. Hua, “Edge-preserving depth map upsampling by joint trilateral filter,” IEEE Transactions on Cybernetics, vol. 48, no. 1, pp. 371-384, Jan. 2018.
[24] J. Lu, D. Min, R. Singh Pahwa, and M. N. Do, “A revisit to MRF-based depth map super-resolution and enhancement,” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 985-988, 2011.
[25] MOBILE3DTV stereo video contents. (Feb. 2009). Mobile 3-D-TV content delivery optimization over DVBH system, [Online]. Available: http://sp.cs.tut.fi/mobile3dtv/stereo-video.
[26] J. Park, H. Kim, Y. W. Tai, M. S. Brown, and I. Kweon, “High quality depth map upsampling for 3D-TOF cameras,” in Proc. IEEE International Conference on Computer Vision, pp. 1623-1630, 2011.
[27] X. Shi, B. Ou, and Z. Qin, “Tailoring reversible data hiding for 3D synthetic images,” Signal Processing: Image Communication, vol. 64, pp. 46-58, May 2018.
[28] The Middlebury Stereo Datasets. [Online]. Available: http://vision.middlebury.edu/stereo/data/
[29] C. Tsai, D. Huang, M. Yang, L. Kang, and Y. Wang, “Contextaware single image super-resolution using locality-constrained group sparse representation,” in Proc. IEEE Visual Communications and Image Processing, pp. 1-6, Nov. 2012.
[30] C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” International Conference on Computer Vision, pp. 839-846, 1998.
[31] R. S. Wang and Y. Wang, “Multiview video sequence analysis, compression, and virtual viewpoint synthesis,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 10, no. 3, pp. 397-410, Apr. 2000.
[32] L. Wang, H. Wu, and C. Pan, “Fast image upsampling via the displacement field,” IEEE Transactions on Image Processing, vol. 23, no. 12, pp. 5123-5135, 2014.
[33] S. Wang, L. Zhang, Y. Liang, and Q. Pan, “Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 2216-2223, Jun. 2012.
[34] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, 2004.
[35] J. Xie, C. C. Chou, R. Feris, and M. T. Sun, “Single depth image super resolution and denoising via coupled dictionary learning with local constraints and shock filtering,” in IEEE International Conference on Multimedia and Expo, pp. 1-6, Jul. 2014.
[36] J. Xie, R. S. Feris, S. S. Yu, and M. T. Sun, “Joint super resolution and denoising from a single depth image,” IEEE Transactions on Multimedia, vol. 17, no. 9, pp. 1525-1537, 2015.
[37] J. Xie, R. S. Feris, and M. T. Sun, “Edge-guided single depth image super resolution,” IEEE Transactions on Image Processing, vol. 25, no. 1, pp. 428-438, Jan. 2016.
[38] J. Yang, J. Wright, T. S. Huang, and Y. Ma, “Image super-resolution via sparse representation,” IEEE Transactions on Image Processing, vol. 19, no. 11, pp. 2861-2873, 2010.
[39] R. Zeyde, M. Elad, and M. Protter, “On single image scale-up using sparse-representations,” in Proc. International Conference on Curves and Surfaces, pp. 711-730, 2010.
[40] Z. Zhang, “Microsoft Kinect sensor and its effect,” IEEE Multimedia, vol. 19, no. 2, pp. 4-10, Feb. 2012.
[41] B. Zhang and J. P. Allebach, “Adaptive bilateral filter for sharpness enhancement and noise removal,” IEEE Transactions on Image Processing, vol. 17, no. 5, pp. 664-678, May 2008.
[42] Y. Zhao, C. Zhu, Z. Chen, and L. Yu, “Depth no-synthesis-error model for view synthesis in 3-D video,” IEEE Transactions on Image Processing, vol. 20, no. 8, pp. 2221-2228, Aug. 2011.

簡易檢索 / 詳目顯示

相關論文