在本篇論文中，我們提出了一個整合型系統，對單張影像做超解析度放大。雖然超解析度技術研究已經歷時多年，現階段仍沒有一個方法可以被廣泛使用於多樣的影像內容或是不同的模糊程度，限制此項技術的實際應用範圍。因此，我們設計了一個整合型系統，融合多方面的超解析度方式，包括內插式、樣本式以及重建式等方法來得到一個適用於多樣影像內容的整合型系統。

提出的系統主要可分為兩部分：產生初始化高解析度的估測值以及透過用學習得到的權重表，整合出最後的高品質影像。首先，我們使用各領域中最簡易的方法來產生初始化影像，也就是代表透過整合分屬不同領域但是簡易的方法，可以有效的增進高解析度影像的品質。接著，我們利用額外的資料庫，透過學習得到一個用於描述真正高解析度影像以及初始預估值之間相互關係的權重表。最後，對任意一張影像，藉由先利用簡易方法產生出初始化影像，再透過權重表將這些初始影像做適當的組合，可以產生一個品質穩定的高解析度影像。

在實驗結果中，我們透過客觀的數據以及使用者評估來展示提出的整合型系統能夠有效地產生高品質影像。

In this thesis, we propose a novel single-image super-resolution system that takes only one low-resolution input image under a learning-based image fusion framework. Although image super-resolution problem has been studied for decades, there is no such an approach that can work well for all different types of images under diverse blur levels, thus limiting most of the state-of-the-art approaches from practical usage. Therefore, we design a learning-based fusion system that integrates several representative image super-resolution approaches, including the interpolation-based, exemplar-based and reconstruction-based methods, for aggregating their advantages to obtain an adaptively fused image super-resolution result.
The proposed approach is decomposed into two principal steps: initial high-resolution image estimation by different methods and adaptive image fusion with learning-based weighted integration. To start with, the initial high-resolution images are estimated by using three representative image scaling approaches; namely, the bicubic interpolation, reconstruction-based and exemplar-based algorithms. Subsequently, a learning-based approach is applied to build a weight table for the adaptive combination of the upscaled images in the patch based manner to obtain the optimal reconstruction. The weight table was learned from an external image dataset by using random projection trees for selecting a number of anchor points and linear polynomial fitting for each group associated with an anchor point. With the learned weight table, we can reconstruct a robust and superior high-resolution image by locally adaptive integration of the three initial upscaled images estimated by three distinct approaches.
Our experiments demonstrate the high-quality image super-resolution results by using the proposed learning-based fusion algorithm. The proposed algorithm outperforms the competing single-image super-resolution algorithms through experimental comparisons on benchmarking images based on objective image metrics as well as subjective user study.

Chapter 1. Introduction 1
1.1 Motivation 1
1.2 Problem Description 2
1.3 Main Contribution 3
1.4 Thesis Organization 4

Chapter 2. Previous Works 5
2.1 Multi-Frame Image Super-Resolution 5
2.2 Single-Image Super-Resolution 7

Chapter 3. Proposed Image Fusion System 10
3.1 System Overview 10
3.2 Initial High-Resolution Image Estimation 14
3.2.1 Interpolation-Based Algorithm 14
3.2.2 Exemplar-Based Algorithm 15
3.2.3 Reconstruction-Based Algorithm 17
3.3 Single-Image Super-Resolution via Hybrid System 19
3.3.1 Learning-Based Adaptive Fusion 19
3.3.2 Anchor Point Selection 21
3.3.3 Weight Table Learning 23
3.3.4 Single-Image Super-Resolution 24

Chapter 4. Experimental Results 26
4.1 Parameters 27
4.1.1 Basic Approaches 27
4.1.2 Integrated System 30
4.2 Training 31
4.3 Evaluation 32
4.3.1 Objective Evaluation 33
4.3.2 Subjective User Study 41
4.3.3 Computational Efficiency 42

Chapter 5. Conclusion 43
References 44

[1]. S. C. Park, M. K. Park, and M. G. Kang. Super-resolution image reconstruction: a technical overview. IEEE Signal Processing Magazine, pages 21–36, 2003.

[2]. P. Milanfar. Super-Resolution Imaging. Taylor & Francis, CRC Press, 2010.

[3]. M. E. Tipping and C. M. Bishop. Bayesian image super-resolution. Advances in Neural Information Processing Systems, 2002.

[4]. J. Sun, J. Sun, Z. Xu, and H.-Y. Shum. Image super-resolution using gradient profile prior. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.

[5]. Q. Shan, Z. Li, J. Jia, and C.-K. Tang. Fast image/video upsampling. ACM Transactions on Graphics (SIGGRAPH), Vol. 27, No. 3, 2008.

[6]. C. Liu, D. Sun. A Bayesian approach to adaptive video super resolution. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.

[7]. W. T. Freeman, T. R. Jones, and E. C. Pasztor. Examplebased super-resolution. IEEE Computer Graphics and Applications, pages 56–65, 2002.

[8]. D. Glasner, S. Bagon, and M. Irani. Super-resolution from a single image. IEEE International Conference on Computer Vision (ICCV), 2009.

[9]. G. Freedman and R. Fattal. Imag and video upscaling from local self-examples. ACM Transactions on Graphics (SIGGRAPH), Vol. 28, No.3, 2010.

[10]. K. I. Kim and Y. Kwon. Single-image super-resolution using sparse regression and natural image prior. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 32(6):1127 –1133, 2010.

[11]. J. Yang, J. Wright, T. Huang, and Y. Ma. Image super-resolution as sparse representation of raw image patches. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.

[12]. S. Wang, Z. D, Y. Liang, and Q. Pan. Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.

[13]. J. Yang, Z. Lin and S. Cohen. Fast Image Super-resolution Based on In-place Example Regression. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.

[14]. C.-Y. Yang, and M.-H. Fast Direct Super-Resolution by Simple Functions. IEEE International Conference on Computer Vision (ICCV), 2013.

[15]. R. Keys. Cubic convolution interpolation for digital image processing. IEEE Transactions on Signal Processing, Acoustics, Speech, and Signal Processing (TASSP), 29(6):1153–1160, 1981.

[16]. Y. Freund, S. Dasgupta, M. Kabra, and N. Verma. Learning the structure of manifolds using random projections. Neural Information Processing Systems (NIPS), 2007.

[17]. M. Grubinger, P. D. Clough, H. Müller and T. Deselaers. The IAPR Benchmark: A New Evaluation Resource for Visual Information Systems. International Conference on Language Resources and Evaluation (LREC), 2006.

[18]. D. Martin, C. Fowlkes, D. Tal and J. Malik. A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics. IEEE International Conference on Computer Vision (ICCV), 2001.

[19]. B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman. LabelMe: A database and web-based tool for image annotation. International Journal of Computer Vision (IJCV), 77(1-3):157 –173, 2008.