A Multi-view Super-Resolution Method with Joint-optimization of Image Fusion and Blind Deblurring = A Multi-view Super-Resolution Method with Joint-optimization of Image Fusion and Blind Deblurring

다국어 초록 (Multilingual Abstract)

Multi-view super-resolution (MVSR) refers to the process of reconstructing a high-resolution (HR) image from a set of low-resolution (LR) images captured from different viewpoints typically by different cameras. These multi-view images are usually obtained by a camera array. In our previous work [1], we super-resolved multi-view LR images via image fusion (IF) and blind deblurring (BD). In this paper, we present a new MVSR method that jointly realizes IF and BD based on an integrated energy function optimization. First, we reformulate the MVSR problem into a multi-channel blind deblurring (MCBD) problem which is easier to be solved than the former. Then the depth map of the desired HR image is calculated. Finally, we solve the MCBD problem, in which the optimization problems with respect to the desired HR image and with respect to the unknown blur are efficiently addressed by the alternating direction method of multipliers (ADMM). Experiments on the Multi-view Image Database¹ of the University of Tsukuba and images captured by our own camera array system demonstrate the effectiveness of the proposed method.

참고문헌 (Reference)

1 Qizi Huangpeng, "Super-resolving blurry multiframe images through multiframe blind deblurring using ADMM"

2 R. Nakashima, "Super-resolved free-viewpoint image synthesis combined with sparse-representation-based super-resolution" 1-6, 2013

3 K. Takahashi, "Super-resolved free-viewpoint image synthesis based on view-dependent depth estimation" 4 : 134-148, 2012

4 C. Guillem, "Super-resolution imaging using a camera array" 39 (39): 1889-1892, 2014

5 U Mudenagudi, "Super Resolution of Images of 3D scenecs" 85-95, 2007

6 S Najafi, "Single and Multi-view Video Super-resolution" McMaster University 2012

7 P. L. Combettes, "Signal recovery by proximal forward-backward splitting" 4 : 1168-1200, 2005

8 F Sroubek, "Robust Multichannel Blind Deconvolution via Fast Alternating Minimization" 21 (21): 1687-1700, 2011

9 K. Venkataraman, "PiCam: An ultra-thin high performance monolithic camera array" 32 (32): 2504-2507, 2013

10 Z. Z. Wang, "On ambiguities in super-resolution modeling" 11 : 678-681, 2004

11 R. Hartley, "Multiple view geometry in computer vision" Cambridge University Press 2000

12 J. Yang, "Image super-resolution via sparse representation" 19 (19): 2861-2873, 2010

13 Z. Wang, "Image quality assessment: from error visibility to structural similarity" 13 (13): 600-612, 2004

14 S. Lertrattanapanich, "High resolution image formation from low resolution frames using Delaunay triangulation" 11 : 1427-1441, 2002

15 B. Wilburn, "High performance imaging using large camera arrays" 24 (24): 765-776, 2005

16 D. Krishnan, "Fast image deconvolution using hyper-laplacian priors. In NIPS" 1033-1041, 2009

17 M. V. Afonso, "Fast Image Recovery Using Variable Splitting and Constrained Optimization" 19 (19): 2345-2356, 2010

18 J. Duchi, "Efficient projections onto the l1-ball for learning in high dimensions" 272-279, 2008

19 S. Boyd, "Distributed optimization and statistical learning via the alternating direction method of multipliers" 3 (3): 1-122, 2011

20 M. S. Almeida, "Deconvolving images with unknown boundaries using the alternating direction method of multipliers" 22 (22): 3074-3086, 2013

21 C. Guillem, "Compact multi-aperture imaging with high-angular-resolution" 32 (32): 411-419, 2015

22 J. Kotera, "Blind deconvolution using alternating maximum a posteriori estimation with heavy-tailed priors" 59-66, 2013

23 D. Gabay, "A dual algorithm for the solution of nonlinear variational problems via finite element approximation" 2 : 17-40, 1976

24 Jun Fan, "A depth-based Multi-view Super-Resolution Method Using Image Fusion and Blind Deblurring" 한국인터넷정보학회 10 (10): 5129-5152, 2016