三維視覺技術在很多領域激發出很多相關的研究主題與轉化應用，對於觀賞者來說，三維影像將有助於他們能夠真實的體驗及欣賞相關娛樂、教育及遊戲作品。而對於許多辨識相關系統而言，其深度資訊可協助其演算法做出更精密的判讀，減少因為彩圖資訊所造成的干擾誤判，深度的獲取就扮演了很重要的角色。傳統電腦視覺的方法是利用雙視角影像中兩眼物件的視差來反推出深度值，但往往會在遮蔽、平滑、及重複圖像區產生許多不可避免的誤差。隨著類神經網路的發展，雙視角深度估測所面臨的問題也漸漸被解決，且在單視角深度估測的準確度也有大幅度提升。本論文提出傳統及深度學習方面的深度估測演算法。對於傳統演算法的初始成本運算，利用了四階普查以及超畫素分割資訊，且成本疊代也利用多種不同搜索框來增加其可靠性。在深度優化方面，因為有了物件分割資訊，我們將可以依照相對應之物件延伸其深度資訊，來達到重建的效果。而在深度學習深度估測方面，我們利用了多尺度特徵來做左右圖像素關係的運算。並且利用多尺度的關係特徵來還原出各尺度深度圖以提升估測表現。除此之外，在單視角估測使用了相對關係深度的計算方式，可以更兼容的運用在各種場域的環境中。實驗結果顯示，本論文所提出的多個方法分別在各種不同條件下都展現不錯的表現。

Three-dimensional vision technologies in many related fields have brought out many research topics and extended applications. For viewers, three-dimensional images will help them to experience and appreciate the related works in entertainment, education and gamming. For many identification-related systems, the depth information can help their algorithms make more precise interpretations and reduce interference or misjudgments caused by color image information. Among them, the generation of depth information plays a very important role. The traditional computer vision methods in use the parallax of the two-eye view images, called stereo matching, to infer the depth value. However, there will obtain many inevitable errors in occlusion, smooth, and repetitive-pattern areas. With the development of neural networks, the problems faced by dual-view depth estimation have gradually been solved, and the accuracy of single-view depth estimation has also been greatly improved. This dissertation first proposes depth estimation algorithms in traditional methods and deep learning architecture. For the initial cost calculation of the traditional algorithm, the quadruple census and super-pixel segmentation information are used, and the cost aggregation also uses a multi-shape window to increase its reliability. In terms of depth optimization, because of the object segmentation information, we will be able to extend the depth information according to the corresponding object to achieve the reconstruction. In terms of deep learning depth estimation, we use multi-scale features to calculate the pixel relationship between left and right images. And use the multi-scale relationship characteristics to restore the depth map of each scale to improve the estimation performance. In addition, the calculation method of relative depth of relationship is used in single-view estimation, which can be more compatibility used in various environments. The experimental results show that the methods proposed in this thesis have achieved good performance under various conditions.

[1] X. Sun, X. Mei, S. Jiao, M. Zhou, and H. Wang, “Stereo matching with reliable disparity propagation,” in Proc. Int. Conf. 3D Image, Model. Process. Vis. Transm., pp. 132–139, May 2011.
[2] H. Lei and C. Jung. "Reliability-Based Discontinuity-Preserving Stereo Matching," IEEE Transactions on Circuits and Systems for Video Technology 26.10: 1970-1975, 2016.
[3] A. F. Bobick and S. S. Intille, "Large occlusion stereo", International Journal of Computer Vision., vol. 33(3), pp. 181–200, Sep. 1999.
[4] Y. Boykov, O. Veksler, and R. Zabih, "Fast approximate energy minimization via graph cuts," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23(11), pp. 1222–1239, Nov. 2001.
[5] P. F. Felzenszwalb and D. P. Huttenlocher, "Efficient belief propagation for early vision," International Journal of Computer Vision, vol. 70(1), pp. 41–54., May 2006.
[6] H. Hirschm¨uller and D. Scharstein, “Evaluation of cost functions for stereo matching,” in Proc. IEEE Conf. CVPR 2007, pp.1–8, Jun.2007.
[7] T.-A. Chang, X. Lu, and J.-F. Yang. "Robust stereo matching with trinary cross color census and triple image-based refinements," EURASIP Journal on Advances in Signal Processing 2017(1): 27, 2017
[8] Y. Men, "A stereo matching algorithm based on four-moded census and relative confidence plane fitting," Chinese Journal of Electronics 24(4): 807-812, 2015.
[9] S.-J. Ko, S. Ji, S. Chae, S.-W. Kim, and D. Lim, “A quaternary census transform based on human visual system for stereo matching,” IEEE Access (8): 116501-116514, 2020.
[10] T-L.Ji, M. K. Sundareshan, and H. Roehrig. "Adaptive image contrast enhancement based on human visual properties," IEEE Transactions on Medical Imaging 13(4): 573-586, 1994.
[11] Y. Chai and X. Cao, "Stereo Matching Algorithm Based on Joint Matching Cost and Adaptive Window," Proc. of IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC). IEEE, 2018.
[12] J. Yang, H. Wang, Z. Ding, Z. Lv, W. Wei and H. Song "Local stereo matching based on support weight with motion flow for dynamic scene," IEEE Access (4): 4840-4847, 2016.
[13] V. Q. Dinh, V. D. Nguyen, and J. W. Jeon, "Robust matching cost function for stereo correspondence using matching by tone mapping and adaptive orthogonal integral image," IEEE Transactions on Image Processing 24(12): 5416-5431, 2015.
[14] J. Žbontar and Y. LeCun, "Computing the Stereo Matching Cost with A Convolutional Neural Network," Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Boston, pp. 1592-1599, 2015.
[15] X. Guo, K. Yang, W. Yang, X. Wang and H. Li, "Group-Wise Correlation Stereo Network," 2019 Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, pp. 3268-3277, 2019.
[16] J. Chang and Y. Chen, "Pyramid Stereo Matching Network," Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 5410-5418.
[17] F. Zhang, V. Prisacariu, R. Yang and P. H. S. Torr, "GA-Net: Guided Aggregation Net for End-To-End Stereo Matching," Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 185-194, 2019.
[18] A. Kendall, H. Martirosyan, S. Dasgupta, P. Henry, R. Kennedy, A. Bachrach and A. Bry, "End-to-End Learning of Geometry and Context for Deep Stereo Regression," Proc. of IEEE International Conference on Computer Vision (ICCV), Venice, pp. 66-75, 2017.
[19] Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., & Navab, N. Deeper depth prediction with fully convolutional residual networks. In Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), pp. 239-248, 2016, October.
[20] Fu, H., Gong, M., Wang, C., Batmanghelich, K., & Tao, D. Deep ordinal regression network for monocular depth estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp, 2002-2011, 2018.
[21] Godard, C., Mac Aodha, O., & Brostow, G. J. Unsupervised monocular depth estimation with left-right consistency. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 270-279. 2017.
[22] Yin, Z., & Shi, J. Geonet: Unsupervised learning of dense depth, optical flow and camera pose. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1983-1992, 2018.
[23] Zheng, C., Cham, T. J., & Cai, J. T2net: Synthetic-to-realistic translation for solving single-image depth estimation tasks. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 767-783, 2018.
[24] T.-A. Chang, X. Lu, and J.-F. Yang. "Robust stereo matching with trinary cross color census and triple image-based refinements," EURASIP Journal on Advances in Signal Processing 2017(1): 27, 2017
[25] Y. Men, "A stereo matching algorithm based on four-moded census and relative confidence plane fitting," Chinese Journal of Electronics 24(4): 807-812, 2015.
[26] S.-J. Ko, S. Ji, S. Chae, S.-W. Kim, and D. Lim, “A quaternary census transform based on human visual system for stereo matching,” IEEE Access (8): 116501-116514, 2020.
[27] T-L.Ji, M. K. Sundareshan, and H. Roehrig. "Adaptive image contrast enhancement based on human visual properties," IEEE Transactions on Medical Imaging 13(4): 573-586, 1994.
[28] K.-J. Yoon, and I. S. Kweon, "Adaptive support-weight approach for correspondence search," IEEE Trans. on Pattern Analysis & Machine Intelligence, vol.28(4), pp. 650-656, 2006.
[29] K. Zhang, J. Lu, and G. Lafruit. "Cross-based local stereo matching using orthogonal integral images," IEEE Trans. on Circuits and Systems for Video Technology 19(7): 1073-1079, 2009.
[30] S. Patil, P. Tanmay, C. Bharath and K. Avinash, “A Comparative Evaluation of SGM Variants (including a New Variant, tMGM) for Dense Stereo Matching, arXiv preprint arXiv:1911.09800, 2019.
[31] S. B. Kang, R. Szeliski and J. Chai, Handling Occlusions in Dense Multi-view Stereo, Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Kauai, HI, USA, 2001, pp. I-I, 2001
[32] Kuo, P. C., Lo, K. L., Tseng, H. K., Lee, K. T., Liu, B. D., & Yang, J. F. Stereoview to Multiview Conversion Architecture for Auto-Stereoscopic 3D Displays. IEEE Transactions on Circuits and Systems for Video Technology, 28(11), 3274-3287, 2017.
[33] H. T. Kuo, VLSI Implementation of Real-Time Stereo Matching and Centralized Texture Depth Packing for 3D Video Broadcasting, M.S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2017.
[34] C. L. Hsieh, A Two-View to Multi-View Conversion System and Its VLSI Implementation for 3D Displays, M. S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2017.
[35] A. Emlek, M. Peker and K. F. Dilaver, Variable window size for stereo image matching based on edge information, Proc. of International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, 2017, pp. 1-4, 2017
[36] T. Y. Sun, Stereo Matching and Depth Refinement on GPU Platform, M. S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2018.
[37] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua and S. Süsstrunk, SLIC Superpixels Compared to State-of-the-Art Superpixel Methods, IEEE Trans. on Pattern Analysis and Machine Intelligence, 34(11), 2274-2282, Nov 2012.
[38] J. Žbontar and Y. LeCun, "Computing the Stereo Matching Cost with A Convolutional Neural Network," Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Boston, pp. 1592-1599, 2015.
[39] A. Kendall, H. Martirosyan, S. Dasgupta, P. Henry, R. Kennedy, A. Bachrach and A. Bry, "End-to-End Learning of Geometry and Context for Deep Stereo Regression," Proc. of IEEE International Conference on Computer Vision (ICCV), Venice, pp. 66-75, 2017.
[40] J. Chang and Y. Chen, "Pyramid Stereo Matching Network," Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 5410-5418,
[41] F. Zhang, V. Prisacariu, R. Yang and P. H. S. Torr, "GA-Net: Guided Aggregation Net for End-To-End Stereo Matching," Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 185-194, 2019.
[42] Y. Zhang, Y. Chen, X. Bai, J. Zhou, K. Yu, Z. Li, & K. Yang, “Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching,” arXiv preprint arXiv:1909.03751, 2019
[43] X. Guo, K. Yang, W. Yang, X. Wang and H. Li, "Group-Wise Correlation Stereo Network," 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, pp. 3268-3277, 2019.
[44] Z. Wu, X. Wu, X. Zhang, S. Wang and L. Ju, "Semantic Stereo Matching with Pyramid Cost Volumes," Proc. of IEEE/CVF International Conference on Computer Vision, Seoul, Korea (South), pp. 7483-7492, 2019.
[45] A. Dosovitskiy, P. Fischer, E. Ilg, P. Hausser, C. Hazirbas, V. Golkov, P. V. D. Smagt, D. Cremers and T. Brox, "FlowNet: Learning Optical Flow with Convolutional Networks," Proc. of IEEE International Conference on Computer Vision, Santiago, pp. 2758-2766, 2015.
[46] N. Mayer, E. Ilg, P. Hausser, P. Fischer, D. Cremers, A. Dosovitskiy and T. Brox, "A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation," Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp. 4040-4048, 2016.
[47] X. Song, X. Zhao, H. Hu, & L. Fang, "Edgestereo: A Context Integrated Residual Pyramid Network for Stereo Matching,” Proc. of Asian Conference on Computer Vision. Springer, Cham, pp. 20-35, 2018.
[48] Z. Liang, Y. Feng, Y. Guo, H. Liu, W. Chen, L. Qiao, L. Zhou and J. Zhang, "Learning for Disparity Estimation Through Feature Constancy," Proc. of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, pp. 2811-2820, 2018.
[49] J. Pang, W. Sun, J. S. Ren, C. Yang and Q. Yan, "Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching," Proc. of IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, pp. 878-886, 2017.
[50] G. Yang, H. Zhao, J. Shi, Z. Deng and J. Jia, "Segstereo: Exploiting Semantic Information for Disparity Estimation," Proceedings of the European Conference on Computer Vision, pp. 636-651, 2018.
[51] Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., & Navab, N. (2016, October). Deeper depth prediction with fully convolutional residual networks. In 2016 Fourth International Conference on 3D Vision (3DV), pp. 239-248.
[52] Fu, H., Gong, M., Wang, C., Batmanghelich, K., & Tao, D. Deep ordinal regression network for monocular depth estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2002-2011, 2018.
[53] Godard, C., Mac Aodha, O., & Brostow, G. J. Unsupervised monocular depth estimation with left-right consistency. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 270-279, 2017.
[54] Yin, Z., & Shi, J. Geonet: Unsupervised learning of dense depth, optical flow and camera pose. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1983-1992, 2018.
[55] Zheng, C., Cham, T. J., & Cai, J. T2net: Synthetic-to-realistic translation for solving single-image depth estimation tasks. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 767-783, 2018.
[56] He, K., Zhang, X., Ren, S., & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
[57] Ronneberger, O., Fischer, P., & Brox, T.. U-net: Convolutional networks for biomedical image segmentation. In Proceedings of International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 234-241, 2015 October.
[58] Simonyan, K., & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
[59] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, 2015.
[60] Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q.. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700-4708, 2017.
[61] Jeon, J., & Lee, S. Reconstruction-based pairwise depth dataset for depth image enhancement using CNN. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 422-438, 2018.
[62] X. Song, G. Yang, X. Zhu, H. Zhou, Z. Wang and J. Shi, AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching, arXiv preprint arXiv:2004.04627, 2020.
[63] Z. Liang, Y. Feng, Y. Guo, H. Liu, W. Chen, L. Qiao & J. Zhang, Learning for disparity estimation through feature constancy. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2811-2820, 2018.
[64] S. Duggal, S. Wang, W.-C. Ma, R. Hu, and R. Urtasun, DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch, In Proceedings of the IEEE International Conference on Computer Vision, pp. 4384-4393, 2019.
[65] Q. Wang, S.Shi, S. Zheng, K. Zhao, and X. Chu, Fadnet: A fast and accurate network for disparity estimation. In Proceedings of 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 101-107, May, 2020.
[66] Y. Hu, W. Wang, H. Yu, W. Zhen and S. Scherer, ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images. arXiv preprint arXiv:2103.07798, 2021
[67] Z. Yang, Y. Jiang, Y. Wu, Z. Lu, W. Li and Q. Liao, "Weber binary pattern and Weber ternary pattern for illumination-robust face recognition," Proc. of IEEE Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2015.
[68] W. S. Fife and J. K. Archibald, "Improved census transforms for resource-optimized stereo vision," IEEE Trans. on Circuits and Systems for Video Technology, vol. 23(1), pp. 60–73, Jan. 2013.
[69] D. Scharstein, R. Szeliski, and R. Zabih, “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,” In Proc. Of IEEE Workshop SMBV, pp. 131–140, 2001.
[70] M. Hariyama, T. Takeuchi, and M. Kameyama. "Reliable stereo matching for highly-safe intelligent vehicles and its VLSI implementation," In Proc. of IEEE Intelligent Vehicles Symposium, 2000.
[71] K. Zhang, J. Lu, and G. Lafruit. "Cross-based local stereo matching using orthogonal integral images," IEEE Trans. on Circuits and Systems for Video Technology 19(7): 1073-1079, 2009.
[72] C. Godard, O. M. Aodha, and G. J. Brostow. "Unsupervised monocular depth estimation with left-right consistency." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 270-279. 2017.
[73] D. Scharstein and C. Pal. “Learning conditional random fields for stereo”. Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, MN, June 2007.
[74] D. Scharstein, H. Hirschmüller, Y. Kitajima, G. Krathwohl, N. Nesic, X. Wang, and P. Westling, High-resolution stereo datasets with subpixel-accurate ground truth, Proc. of German Conference on Pattern Recognition (GCPR 2014), Münster, Germany, Sep 2014.
[75] P. C. Kuo, K. L. Lo, H. K. Tseng, K. T. Lee, B. D. Liu, and J. F. Yang, “Stereoview to Multiview Conversion Architecture for Auto-Stereoscopic 3D Displays,” IEEE Transactions on Circuits and Systems for Video Technology 28(11): 3274-3287, 2017.
[76] A. Emlek, M. Peker and K. F. Dilaver. “Variable window size for stereo image matching based on edge information,” Prof. of 2017 International Artificial Intelligence and Data Processing Symposium (IDAP). IEEE, pp. 1-4, 2017.
[77] K. Zhang, J. Lu and G. Lafruit, Cross-Based Local Stereo Matching Using Orthogonal Integral Images, IEEE Trans. on Circuits and Systems for Video Technology, 19(7), 1073-1079, July 2009.
[78] D. Scharstein and R. Szeliski, High-accuracy stereo depth maps using structured light, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), volume 1, Madison, WI, pp. 195-202 June 2003.
[79] D. Scharstein and C. Pal, Learning conditional random fields for stereo, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, MN, Jun 2007.
[80] D. Scharstein, H. Hirschmüller, Y. Kitajima, G. Krathwohl, N. Nesic, X. Wang, and P. Westling, High-resolution stereo datasets with subpixel-accurate ground truth, German Conference on Pattern Recognition (GCPR 2014), Münster, Germany, Sep 2014.
[81] K.-.J Yoon and I. S. Kweon, Adaptive Support-Weight Approach for Correspondence Search, IEEE Trans. on Pattern Analysis and Machine Intelligence, 28(4), 650-656, April 2006.
[82] Liu, Zhi-chao, Li-hong Xu, and Chao-feng Lin. An Improved Stereo Matching Algorithm Applied to 3D Visualization of Plant Leaf. 2015 8th International Symposium on Computational Intelligence and Design (ISCID). 2. IEEE, 2015.
[83] Emlek, A., Peker, M., & Dilaver, K. F., Variable window size for stereo image matching based on edge information, 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), IEEE, pp. 1–4, September 2017.
[84] T. Y. Sun, Stereo Matching and Depth Refinement on GPU Platform, M. S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2018.
[85] Song, X., Yang, G., Zhu, X., Zhou, H., Wang, Z., & Shi, J, AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching, arXiv preprint arXiv:2004.04627. 2020.
[86] Liang, Z., Feng, Y., Guo, Y., Liu, H., Chen, W., Qiao, L., ... & Zhang, J, Learning for disparity estimation through feature constancy. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2811-2820, 2018.
[87] Duggal, Shivam, Shenlong Wang, Wei-Chiu Ma, Rui Hu, and Raquel Urtasun, DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch., In Proceedings of the IEEE International Conference on Computer Vision, pp. 4384-4393, 2019.
[88] K. J. Hsu, GPU Implementation for Centralized Texture Depth Depacking and Depth Image-based Rendering, M. S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2017.
[89] Kuo, P. C., Lo, K. L., Tseng, H. K., Lee, K. T., Liu, B. D., & Yang, J. F. Stereoview to Multiview Conversion Architecture for Auto-Stereoscopic 3D Displays. IEEE Transactions on Circuits and Systems for Video Technology, 28(11), 3274-3287, 2017.
[90] H. T. Kuo, VLSI Implementation of Real-Time Stereo Matching and Centralized Texture Depth Packing for 3D Video Broadcasting, M.S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2017.
[91] C. L. Hsieh, A Two-View to Multi-View Conversion System and Its VLSI Implementation for 3D Displays, M. S. Thesis, National Cheng Kung University, Tainan, Taiwan, July 2017.
[92] G. Tech, K. Wegner, Y. Chen, and S. Yea, 3D HEVC Test Model 3. Document: JCT3VC1005. Draft 3 of 3D-HEVC Test Model Description. Geneva, 2013.
[93] D. Rusanovskyy, K. Müller, and A. Vetro, Common Test Conditions of 3DV Core Experiments, Joint Collaborative Team on 3D Video Coding Extensions of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11, Document no. JC3VC-E1100, Vienna, Aug 2013.
[94] J.-F. Yang, K.-T. Lee, G.-C. Chen, W.-J. Yang and Lu Yu, A YCbCr Color Depth Packing Method and Its Extension for 3D Video Broadcasting Services, IEEE Trans. on Circuits and Systems for Video Technology, ISSN: 1051-8215, Online ISSN: 1558-2205 Digital Object Identifier: 10.1109/TCSVT.2019.29342541, pp.1-11, 2019.
[95] W.-J. Yang, J.-F. Yang, G.-C. Chen, P.-C. Chung and M. F. Chung, “An Assigned Color Depth Packing Method with Centralized Texture Depth Packing Formats for 3D VR Broadcasting Services”, IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9(1), 122-132, March 2019
[96] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 770-778, 2016.
[97] F. Aleotti, M. Poggi, F. Tosi, and S. Mattoccia. "Learning end-to-end scene flow by distilling single tasks knowledge," Proc. of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 10435-10442. 2020.
[98] A. Geiger, P. Lenz and R. Urtasun, "Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite," Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, pp. 3354-3361, 2012.
[99] K. Yee, and A. Chakrabarti. "Fast Deep Stereo with 2D Convolutional Processing of Cost Signatures," Proc. of IEEE Winter Conference on Applications of Computer Vision, pp. 183-191, 2020.
[100] X. Song, G. Yang, X. Zhu, H. Zhou, Z. Wang and J. Shi. "AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching." arXiv preprint arXiv:2004.04627, 2020.
[101] P. Knobelreiter, C. Sormann, A. Shekhovtsov, F. Fraundorfer and T. Pock. "Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems." Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7900-7909. 2020.