請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/20065
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 郭大維(Tei-Wei Kuo) | |
dc.contributor.author | Han-Yi Lin | en |
dc.contributor.author | 林翰毅 | zh_TW |
dc.date.accessioned | 2021-06-08T02:39:32Z | - |
dc.date.copyright | 2021-02-26 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2021-02-19 | |
dc.identifier.citation | K. W. Tan, T. Okoshi, A. Misra, and R. K. Balan. FOCUS: A Usable Effective Approach to OLED Display Power Management. In Proc. of ACM UbiComp, pages 573–582, 2013. Tianfan Xue, Baian Chen, Jiajun Wu, Donglai Wei, and William T. Freeman. Video enhancement with taskoriented flow. IJCV, 2019. Simon Baker, Daniel Scharstein, J. P. Lewis, Stefan Roth, Michael J. Black, and Richard Szeliski. A database and evaluation methodology for optical flow. In ICCV, 2007. Ce Liu and Deqing Sun. A bayesian approach to adaptive video super resolution. In CVPR, 2011. Jordi PontTuset, Federico Perazzi, Sergi Caelles, Pablo Arbelaez, Alexander SorkineHornung, and Luc Van Gool. The 2017 davis challenge on video object segmentation. arXiv:1704.00675, 2017. C.K. Kang, C.H. Lin, and P.C. Hsiu. A WinWin Camera: QualityEnhanced PowerSaving Images on Mobile OLED Displays. In Proc. of IEEE/ACM ISLPED, pages 267–272, 2015. Songtao He, Yunxin Liu, and Hucheng Zhou. Optimizing Smartphone Power Consumption through Dynamic Resolution Scaling. In Proc. of ACM MobiCom, pages 27–39, 2015. M. Dong and L. Zhong. Chameleon: A ColorAdaptive Web Browser for Mobile OLED Displays. In Proc. of ACM MobiSys, pages 85–98, 2011. M. Dong and L. Zhong. Power Modeling and Optimization for OLED Displays. IEEE Trans. on Mobile Computing, 11(9):1587–1599, 2012. X. Chen, J. Zheng, Y. Chen, M. Zhao, and C. J. Xue. QualityRetaining OLED Dynamic Voltage Scaling for Video Streaming Applications on Mobile Devices. In Proc. of IEEE/ACM DAC, pages 1000–1005, 2012. C.H. Lin, C.K. Kang, and P.C. Hsiu. Catch Your Attention: QualityRetaining Power Saving on Mobile OLED Displays. In Proc. of IEEE/ACM DAC, pages 1–6, 2014. D. Shin, Y. Kim, N. Chang, and M. Pedram. Dynamic Voltage Scaling of OLED Displays. In Proc. of IEEE/ACM DAC, pages 53–58, 2011. Xiang Chen, Jiachen Mao, Jiafei Gao, Kent W. Nixon, and Yiran Chen. MORPh: Mobile OLEDfriendly Recording and Playback System for Low Power Video Streaming. In Proc. of IEEE/ACM DAC, pages 153:1–153:6, 2016. J. BettsLaCroix. Selective Dimming of OLED Displays. US Patent 0149223 A1, 2010. X. Chen, K. W. Nixon, H. Zhou, Y. Liu, and Y. Chen. FingerShadow: An OLED Power Optimization based on Smartphone Touch Interactions. In Proc. of USENIX HotPower, pages 6:1–6:5, 2014. M. Dong, Y. K. Choi, and L. Zhong. PowerSaving Color Transformation of Mobile Graphical User Interfaces on OLEDbased Displays. In Proc. of IEEE/ACM ISLPED, pages 339–342, 2009. Jiadi Yu, Haofu Han, Hongzi Zhu, Yingying Chen, Jie Yang, Yanmin Zhu, Guangtao Xue, and Minglu Li. Sensing HumanScreen Interaction for EnergyEfficient Frame Rate Adaptation on Smartphones. IEEE Trans. on Mobile Computing, 14(8):1698–1711, 2015. Robert G Keys. Cubic convolution interpolation for digital image processing. 1981. Xinbo Gao, Kaibing Zhang, Dacheng Tao, and Xuelong Li. Image superresolution with sparse neighbor embedding. IEEE TIP, 2012. Roman Zeyde, Michael Elad, and Matan Protter. On single image scaleup using sparserepresentations. In Curves and Surfaces, 2012. Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Image superresolution using deep convolutional networks. 2016. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In CVPR, 2016. Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. Accurate image superresolution using very deep convolutional networks. In CVPR, 2016. Ying Tai, Jian Yang, and Xiaoming Liu. Image superresolution via deep recursive residual network. In CVPR, 2017. Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu. Residual dense network for image superresolution. In CVPR, 2018. Muhammad Haris, Gregory Shakhnarovich, and Norimichi Ukita. Deep backprojection networks for superresolution. In CVPR, 2018. Simon Baker, Daniel Scharstein, J. P. Lewis, Stefan Roth, Michael J. Black, and Richard Szeliski. A database and evaluation methodology for optical flow. IJCV, 2011. Zhefei Yu, Houqiang Li, Zhangyang Wang, Zeng Hu, and Chang Wen Chen. Multilevel video frame interpolation: Exploiting the interaction among different levels. TCSVT, 2013. Christian Bailer, Bertram Taetz, and Didier Stricker. Flow fields: Dense correspondence fields for highly accurate large displacement optical flow estimation. 2019. Simon Niklaus, Long Mai, and Feng Liu. Video frame interpolation via adaptive convolution. In CVPR, 2017. Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, and Aseem Agarwala. Video frame synthesis using deep voxel flow. In ICCV, 2017. Wenbo Bao, WeiSheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and MingHsuan Yang. Depthaware video frame interpolation. In CVPR, 2019. Oded Shahar, Alon Faktor, and Michal Irani. Spacetime superresolution from a single video. In CVPR, 2011. Manoj Sharma, Santanu Chaudhury, and Brejesh Lall. Spacetime superresolution using deep learning based framework. 2017. YunChun Chen, YenYu Lin, MingHsuan Yang, and JiaBin Huang. Crdoco: Pixellevel domain transfer with crossdomain consistency. In CVPR, 2019. YuLun Liu, YiTung Liao, YenYu Lin, and YungYu Chuang. Deep video frame interpolation using cyclic frame generation. In AAAI, 2019. HsinYi Chen, YenYu Lin, and BingYu Chen. Cosegmentation guided hough transform for robust feature matching. 2015. YunChun Chen, PoHsiang Huang, LiYu Yu, JiaBin Huang, MingHsuan Yang, and YenYu Lin. Deep semantic matching with foreground detection and cycleconsistency. In ACCV, 2018. YunChun Chen, YenYu Lin, MingHsuan Yang, and JiaBin Huang. Show, match and segment: Joint weakly supervised learning of semantic matching and object cosegmentation. 2020. ChungChi Tsai, Weizhi Li, KuangJui Hsu, Xiaoning Qian, and YenYu Lin. Image cosaliency detection and cosegmentation via progressive joint optimization. IEEE TIP, 2019. Yuliang Zou, Zelun Luo, and JiaBin Huang. Dfnet: Unsupervised joint learning of depth and flow using crosstask consistency. In ECCV, 2018. WeiSheng Lai, JiaBin Huang, Oliver Wang, Eli Shechtman, Ersin Yumer, and MingHsuan Yang. Learning blind video temporal consistency. In ECCV, 2018. Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, and Jiří Matas. Deblurgan: Blind motion deblurring using conditional adversarial networks. In CVPR, 2018. Hee Seok Lee and Kuoung Mu Lee. Dense 3d reconstruction from severely blurred images using a single moving camera. In CVPR, 2013. Christopher Mei and Ian Reid. Modeling and generating complex motion blur for realtime tracking. In CVPR, 2008. Hee Seok Lee, Junghyun Kwon, and Kyoung Mu Lee. Simultaneous localization, mapping and deblurring. In ICCV, 2011. Soo Ye Kim, Jihyong Oh, and Munchurl Kim. Jsigan: Ganbased joint superresolution and inverse tonemapping with pixelwise taskspecific filters for uhd hdr video. In AAAI, 2020. YuLun Liu, WeiSheng Lai, YuSheng Chen, YiLung Kao, MingHsuan Yang, YungYu Chuang, and JiaBin Huang. Singleimage hdr reconstruction by learning to reverse the camera pipeline. In CVPR, 2020. Seungjun Nah, Tae Hyun Kim, and Kyoung Mu Lee. Deep multiscale convolutional neural network for dynamic scene deblurring. In CVPR, 2017. Orest Kupyn, Tetiana Martyniuk, Junru Wu, and Zhangyang Wang. Deblurganv2: Deblurring (ordersofmagnitude) faster and better. In ICCV, 2019. Hongguang Zhang, Yuchao Dai, Hongdong Li, and Piotr Koniusz. Deep stacked hierarchical multipatch network for image deblurring. In CVPR, 2019. Dongwon Park, Dong Un Kang, Jisoo Kim, and Se Young Chun. Multitemporal recurrent neural networks for progressive nonuniform single image deblurring with incremental temporal training. In ECCV, 2020. Yaroslav Ganin and Victor Lempitsky. Unsupervised domain adaptation by backpropagation. In ICML, 2015. Shai BenDavid, John Blitzer, Koby Crammer, and Fernando Pereira. Analysis of representations for domain adaptation. NeurIPS, 19:137–144, 2006. Fitsum A. Reda, Deqing Sun, Aysegul Dundar, Mohammad Shoeybi, Guilin Liu, Kevin J. Shih, Andrew Tao, Jan Kautz, and Bryan Catanzaro. Unsupervised video interpolation using cycle consistency. In ICCV, 2019. Daniel Glasner, Shai Bagon, and Michal Irani. Superresolution from a single image. In ICCV, 2009. Tomer Michaeli and Michal Irani. Nonparametric blind superresolution. In ICCV, 2013. JiaBin Huang, Abhishek Singh, and Narendra Ahuja. Single image superresolution from transformed selfexemplars. In CVPR, 2015. JunJie Huang, Tianrui Liu, Pier Luigi Dragotti, and Tania Stathaki. Srhrf+: Selfexample enhanced single image superresolution using hierarchical random forests. In CVPRW, 2017. Assaf Shocher, Nadav Cohen, and Michal Irani.“zeroshot”superresolution using deep internal learning. In CVPR, 2018. Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, and Timothy Lillicrap. Metalearning with memoryaugmented neural networks. In ICML, 2016. Chelsea Finn, Pieter Abbeel, and Sergey Levine. Modelagnostic metalearning for fast adaptation of deep networks. In ICML, 2017. Jake Snell, Kevin Swersky, and Richard Zemel. Prototypical networks for fewshot learning. In NeurIPS, 2017. Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. Learning to compare: Relation network for fewshot learning. In CVPR, 2018. Guiguang Ding, Yuchen Guo, Kai Chen, Chaoqun Chu, Jungong Han, and Qionghai Dai. Decode: Deep confidence network for robust image classification. IEEE TIP, 2019. Li Xu and Jiaya Jia. Twophase kernel estimation for robust motion deblurring. In ECCV, 2010. Oliver Whyte, Josef Sivic, Andrew Zisserman, and Jean Ponce. Nonuniform deblurring for shaken images. IJCV, 2012. Florent CouzinieDevy, Jian Sun, Karteek Alahari, and Jean Ponce. Learning to estimate and remove nonuniform image blur. In CVPR, 2013. Jian Sun, Wenfei Cao, Zongben Xu, and Jean Ponce. Learning a convolutional neural network for nonuniform motion blur removal. In CVPR, 2015. Dong Gong, Jie Yang, Lingqiao Liu, Yanning Zhang, Ian Reid, Chunhua Shen, Anton Van Den Hengel, and Qinfeng Shi. From motion blur to motion flow: a deep learning solution for removing heterogeneous motion blur. In CVPR, 2017. Daniel Zoran and Yair Weiss. From learning models of natural image patches to whole image restoration. In ICCV, 2011. Xin Tao, Hongyun Gao, Xiaoyong Shen, Jue Wang, and Jiaya Jia. Scalerecurrent network for deep image deblurring. In CVPR, 2018. Muriel Boucart, Christine Moroni, Miguel Thibaut, Sebastien Szaffarczyk, and Michelle Greene. Scene Categorization at Large Visual Eccentricities. Vision Research, 86:35–42, 2013. Hans Strasburger, Ingo Rentschler, and Martin Jüttner. Peripheral vision and pattern recognition: A review. Journal of Vision, 11(4):13, 2011. Michel Millodot. Dictionary of Optometry and Visual Science. Butterworth Heinemann Elsevier, 7 edition, 2009. Kalloniatis M. and Luu C. Light and dark adaptation. In Webvision: The Organization of the Retina and Visual System, 2005. Kimihiro Yamanaka and Atsushi Minochi. Measurement of Useful Field of View during Ocular Following Response. In Proc. of HCI, pages 455–459, 2013. Wenzhe Shi, Jose Caballero, Ferenc Huszar, Johannes Totz, Andrew P. Aitken, Rob Bishop, Daniel Rueckert, and Zehan Wang. Realtime single image and video superresolution using an efficient subpixel convolutional neural network. In CVPR, 2016. Huaizu Jiang, Deqing Sun, Varun Jampani, MingHsuan Yang, Erik G. LearnedMiller, and Jan Kautz. Super slomo: High quality estimation of multiple intermediate frames for video interpolation. In CVPR, 2018. Hancheng Zhu, Leida Li, Jinjian Wu, Weisheng Dong, and Guangming Shi. Metaiqa: Deep metalearning for noreference image quality assessment. In CVPR, 2020. Seobin Park, Jinsu Yoo, Donghyeon Cho, Jiwon Kim, and Tae Hyun Kim. Fast adaptation to superresolution networks via metalearning. In ECCV, 2020. Jae Woong Soh, Sunwoo Cho, and Nam Ik Cho. Metatransfer learning for zeroshot superresolution. In CVPR, 2020. Myungsub Choi, Janghoon Choi, Sungyong Baik, Tae Hyun Kim, and Kyoung Mu Lee. Sceneadaptive video frame interpolation via metalearning. In CVPR, 2020. Tae Hyun Kim, Kyoung Mu Lee, Bernhard Scholkopf, and Michael Hirsch. Online video deblurring via dynamic temporal blending network. In CVPR, 2017. Shuochen Su, Mauricio Delbracio, Jue Wang, Guillermo Sapiro, Wolfgang Heidrich, and Oliver Wang. Deep video deblurring for handheld cameras. In CVPR, 2017. Seungjun Nah, Sungyong Baik, Seokil Hong, Gyeongsik Moon, Sanghyun Son, Radu Timofte, and Kyoung Mu Lee. Ntire 2019 challenge on video deblurring and superresolution: Dataset and study. In CVPRW, 2019. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/20065 | - |
dc.description.abstract | 近年來由於資訊技術與數位生活的蓬勃發展,我們的生活中充滿了各式各樣的顯示系統,小至智慧型手錶與智慧型手機,大至電腦螢幕與電視螢幕等。隨著材料與製程的進步,視覺效果更清晰的發光材料也被廣泛的應用,並且顯示器的像素密度與解析度也持續提升。然而顯示技術的進步也帶來了許多新的問題,例如新的顯示器使用有機發光二極體(OLED)做為發光元件,但新型態的元件其發光原理與以往的液晶螢幕(LCD)發光原理與功耗模型有很大的不同,這使得傳統的電源管理方法,並無法直接應用在新型態的OLED顯示器上。另一項問題是像素密度不對稱,近年來製程進步讓顯示器的像素密度提升,但有部分錄影設備的解析度還沒相對應的提升,因此需要一個超解析度的方法來將影片提升至對應的解析度。另外隨著顯示器解析度的提升,影片會以較高的解析度呈現在顯示器上,此時若影片中有模糊區域,則模糊將會被放大,因此我們需要一個去模糊的方法來應對。本篇博士論文針對以上顯示器進步所帶來的問題進行探討與研究,提出了對應的方法來解決。針對第一個議題,我們考量人眼視覺特性提出了一個OLED的電源管理機制。接著為了讓影片解析度能夠對應到顯示器的像素密度,我們同時考量空間域與時間域的相依性,提出一個同時增加空間域與時間域解析度的方法。最後我們提出一個自適應新場景的去模糊網路,可以在適應新的場景後再進行去模糊。在本篇論文中所提出的方法,透過實驗驗證都有相當程度的效能提升。 | zh_TW |
dc.description.abstract | In the past few decades, due to the popularity of information technology, our lives have been filled with various display systems, ranging from smartwatches and smartphones to computer screens and TV screens. With the advancement of materials and manufacturing processes, display materials with better imaging quality are widely used, the pixel density and resolution of displays have also increased year by year. However, the progress of display technology has also brought many new issues. For example, the next-generation display uses organic light-emitting diodes (OLED) as the light-emitting elements, but the light-emitting principle of OLED is very different from the LCD. The power model is also different, which makes the traditional power management method cannot be directly applied to the OLED display. Another issue is the problem of asymmetry pixel density. In recent years, advances in manufacturing have increased the pixel density of displays. However, the resolution of many videos has not yet been improved to such a high resolution, so we need a super-resolution approach to up-scale the resolution of videos. In addition, as the resolution of the monitor increases, the video will be displayed on the monitor with a higher resolution. At this time, if there is a blurred area in the video, the blur will be enlarged. Therefore, we need a deblurring method to deal with. This PhD thesis proposes corresponding methods to solve these issues. In response to the first issue, we have proposed a power management mechanism for OLED considering the characteristics of human visual acuity. Then, in order to make the video resolution correspond to the pixel density of the display, we propose a spatiotemporal super-resolution method. Finally, we propose a scene-adaptive deblurring network, which can adapt to novel scenes. The proposed methods are verified through experiments, and have a considerable performance improvement. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T02:39:32Z (GMT). No. of bitstreams: 1 U0001-1902202110290100.pdf: 20742108 bytes, checksum: 3ca48ba20dd034b63458807749ca6d8d (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 口試委員會審定書 i 中文摘要 ii Abstract iii Contents iv List of Figures vii List of Tables viii 1 Introduction 1 1.1 Introduction 1 1.2 Contributions 2 2 Background and Related Work 4 2.1 Energyefficient Display Power Management 4 2.1.1 OLED Display Panel 4 2.1.2 Lowpower Techniques for OLED Display 5 2.1.3 Interactive Applications on Mobile Devices 6 2.2 Spatiotemporal Superresolution 7 2.2.1 Spatial Superresolution 7 2.2.2 Temporal SuperResolution 8 2.2.3 Spatiotemporal Superresolution 9 2.2.4 Cycle Consistency 10 2.3 Sceneadaptive video deblurring 10 2.3.1 Image and Video Deblurring 11 2.3.2 Metalearning 12 3 ShiftMask: Dynamic OLED Power Shifting Based on Visual Acuity for Interactive Mobile Applications 14 3.1 Observation and Motivation 14 3.2 AcuityAware Dynamic Partial Dimming 16 3.2.1 Static Scenes 16 3.2.2 Focus Changes 17 3.2.3 Screen Scrolling 18 3.3 ShiftMask Implementation 20 3.4 Performance Evaluation 22 3.4.1 Experiment Setup 22 3.4.2 Experiment Results 24 4 Spatiotemporal SuperResolution with CrossTask Consistency and its Semisupervised Extension 27 4.1 Observation and Motivation 27 4.2 Problem Definition 28 4.3 Network Architecture 30 4.4 Objective Function 30 4.4.1 Reconstruction Loss LR 31 4.4.2 Crossstream Consistency Loss LC 31 4.5 Semisupervised Learning 32 4.6 Implementation Details 32 4.7 Experimental Results 33 4.7.1 Datasets 33 4.7.2 Ablation Studies 33 5 Metadeblurring: A Metalearning Approach to Adaptive Video Deblurring 42 5.1 Observation and Motivation 42 5.2 Metadeblurring Overview 43 5.3 Support Set Generation 45 5.4 Metatraining 47 5.5 Metainference 48 5.6 Implementation Detail 48 5.7 Experimental Results 49 5.7.1 Datasets 49 5.7.2 Comparisons with Existing Methods 49 5.7.3 Ablation Studies and Performance Analysis 53 6 Conclusions and Future Work 55 6.1 Conclusions 55 6.2 Future Work 56 Bibliography 57 | |
dc.language.iso | en | |
dc.title | 基於視覺顯示之節能與品質提升技術 | zh_TW |
dc.title | Visual-sensation-aware Content Processing for Energy-efficient and Quality-enhanced Display | en |
dc.type | Thesis | |
dc.date.schoolyear | 109-1 | |
dc.description.degree | 博士 | |
dc.contributor.coadvisor | 林彥宇(Yen-Yu Lin) | |
dc.contributor.oralexamcommittee | 洪士灝(Shih-Hao Hung),施吉昇(Chi-Sheng Shih),莊永裕(Yung-Yu Chuang),修丕承(Pi-Cheng Hsiu) | |
dc.subject.keyword | 行動裝置節能,OLED顯示節能,影像品質提升,電腦視覺,深度學習,超解析度,影格內插,去模糊, | zh_TW |
dc.subject.keyword | Energy-efficient mobile display,Energy-efficient OLED display,Video quality enhancement,Computer vision,Deep learning,Super-resolution,Frame interpolation,Deblurring, | en |
dc.relation.page | 65 | |
dc.identifier.doi | 10.6342/NTU202100749 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2021-02-19 | |
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 | |
---|---|---|---|
U0001-1902202110290100.pdf 目前未授權公開取用 | 20.26 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。