Light‐field image super‐resolution with depth feature by multiple‐decouple and fusion module
Open Access
- 7 January 2024
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 60 (1)
Abstract
Light‐field (LF) images offer the potential to improve feature capture in live scenes from multiple perspectives, and also generate additional normal vectors for performing super‐resolution (SR) image processing. With the benefit of machine learning, established AI‐based deep CNN models for LF image SR often individualize the models for various resolutions. However, the rigidity of these approaches for actual LF applications stems from the considerable diversity in angular resolution among LF instruments. Therefore, an advanced neural network proposal is required to utilize a CNN‐based model for super‐resolving LF images with different resolutions obtained from provided features. In this work, a preprocessing to calculate the depth channel from given LF information is first presented, and then a multiple‐decouple and fusion module is introduced to integrate the VGGreNet for the LF image SR, which collects global‐to‐local information according to the CNN kernel size and dynamically constructs each view through a global view module. Besides, the generated features are transformed to a uniform space to perform final fusion, achieving global alignment for precise extraction of angular information. Experimental results show that the proposed method can handle benchmark LF datasets with various angular and different resolutions, reporting the effectiveness and potential performance of the method.Keywords
This publication has 22 references indexed in Scilit:
- Satellite Video Super-Resolution via Multiscale Deformable Convolution Alignment and Temporal Grouping ProjectionIEEE Transactions on Geoscience and Remote Sensing, 2021
- A General Method for Generating Discrete Orthogonal MatricesIEEE Access, 2021
- End-to-End Light Field Spatial Super-Resolution Network Using Multiple Epipolar GeometryIEEE Transactions on Image Processing, 2021
- Light Field Image Super-Resolution Using Deformable ConvolutionIEEE Transactions on Image Processing, 2020
- Spatial-Angular Interaction for Light Field Image Super-Resolution2020
- Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization2020
- Residual Networks for Light Field Image Super-Resolution2019
- Enhanced Deep Residual Networks for Single Image Super-Resolution2017
- Accurate depth map estimation from a lenslet light field camera2015
- Gram‐Schmidt orthogonalization: 100 years and moreNumerical Linear Algebra with Applications, 2012