Spatial-Angular Interaction for Light Field Image Super-Resolution

Wang, Yingqian; Wang, Longguang; Yang, Jungang; An, Wei; Yu, Jingyi; Guo, Yulan

doi:10.1007/978-3-030-58592-1_18

Cited by 148 publications

(157 citation statements)

References 45 publications

Supporting

Mentioning

157

Contrasting

Order By: Relevance

“…From (6), it can be seen that the signal spectra are modulated by the interpolation kernel spectra. If K is low pass, as in general an interpolation kernel should be, the bandwidth of K ω x is limited.…”

Section: Analysis Of Interpolationmentioning

confidence: 99%

High‐precision refocusing method with one interpolation for camera array images

Yang

Xiao

Wang

et al. 2020

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Camera array image refocusing can change the in-focus region so that objects lying on a specified plane are in focus, whereas objects lying off this plane are blurred. Existing refocusing methods for camera array or light field images usually contain two interpolations. Since interpolation brings distortion, especially on the sharp edge in the images, existing methods are not sufficiently precise. In order to improve the quality of the refocusing result, the authors propose a high-precision method to refocus camera array images. They first back-project the pixel coordinates to a corresponding location on the focal plane in the world coordinate. Then they reproject the world coordinates to the pixel coordinates by using the parameters of each camera in the array. After that, they align the images with the focal plane by employing interpolation according to the acquired pixel coordinates. Finally, they get the synthetic image refocused on the focal plane by averaging the resulted images. In the proposed method, only one interpolation is used. So that it alleviates the quality degradation of the refocused image compared to the existing methods. Experiments on real-world scenes (captured by their self-developed light field devices) demonstrate that their method can yield better results than the existing methods.

show abstract

Section: Analysis Of Interpolationmentioning

confidence: 99%

High‐precision refocusing method with one interpolation for camera array images

Yang

Xiao

Wang

et al. 2020

IET Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, subject to the physical size of the pixel sensor inside light field cameras, there is a tradeoff between spatial resolution and angular resolution [9],i.e., to improve spatial resolution, we need to reduce the angular resolution. Generally, sparse angular sampling is utilized to retain high spatial resolution for more spatial details displaying [10]. However, Sparse angular sampling could cause some severe aliasing problems in refocusing [11], ghosting effect in light field rendering [12], and low accuracy in the depth estimation [13].…”

Section: Introductionmentioning

confidence: 99%

Fast Light Field Angular Resolution Enhancement Using Convolutional Neural Network

et al. 2021

View full text Add to dashboard Cite

Current light field angular super-resolution algorithm based on deep learning has excessive computation cost and low operational efficiency, for sequentially up-sampling on each lenslet region of the light field image. In this paper, we propose a novel convolutional neural network to fastly enhance the angular resolution, via wholesale up-sampling lenslet regions. Firstly, the network simultaneously extracts the angular information of all lenslet regions on the input light field image. Then, from the extracted angular information, four feature maps are predicted. Especially, the angular resolution of each feature map is the same as that of the input light field image. Finally, to enhance the angular resolution, we integrate four feature maps into one image, by referring to angular information arrangement in lenslet regions. The experimental results verify the effectiveness of our proposed method. We only need 11.95s to enhance(actually double) the angular resolution of one light field image with 2562×3724 pixels, which surpasses 20 times faster than the state-ofthe-art method. Meanwhile, our method also achieves average PSNR gains of 0.39 dB. INDEX TERMS Light-field(LF), angular super-resolution, convolutional neural network(CNN).

show abstract

“…According to the number of input LR images, the SR can be classified into multi-image super-resolution (MISR) [3][4][5] and single-image super-resolution (SISR) [6][7][8]. MISR uses the complementary information provided by multiple images of the same scene to enhance resolution.…”

Section: Introductionmentioning

confidence: 99%

Single-Image Super-Resolution Using Panchromatic Gradient Prior and Variational Model

Song

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Single-image super-resolution (SISR) is a resolution enhancement technique and is known as an ill-posed problem. Motivated by the idea of pan-sharping, we propose a novel variational model for SISR. The structure tensor of the input low-resolution image is exploited to obtain the gradient of an imaginary panchromatic image. Then, by constraining the gradient consistency, the image edges and details can be better recovered during the procedure of restoration of high-resolution images. Besides, we resort to the nonlocal sparse and low-rank regularization of image patches to further improve the super-resolution performance. The proposed variational model is efficiently solved by ADMM-based algorithm. We do extensive experiments in natural images and remote sensing images with different magnifying factors and compare our method with three classical super-resolution methods. The subjective visual impression and quantitative evaluation indexes both show that our method can obtain higher-quality results.

show abstract

Spatial-Angular Interaction for Light Field Image Super-Resolution

Cited by 148 publications

References 45 publications

High‐precision refocusing method with one interpolation for camera array images

High‐precision refocusing method with one interpolation for camera array images

Fast Light Field Angular Resolution Enhancement Using Convolutional Neural Network

Single-Image Super-Resolution Using Panchromatic Gradient Prior and Variational Model

Contact Info

Product

Resources

About