Research Article
An Improved 4D Convolutional Neural Network for Light Field Reconstruction
@INPROCEEDINGS{10.1007/978-3-031-55471-1_9, author={Qiuming Liu and Ruiqin Li and Ke Yan and Yichen Wang and Yong Luo}, title={An Improved 4D Convolutional Neural Network for Light Field Reconstruction}, proceedings={Mobile Networks and Management. 13th EAI International Conference, MONAMI 2023, Yingtan, China, October 27-29, 2023, Proceedings}, proceedings_a={MONAMI}, year={2024}, month={3}, keywords={Light field reconstruction 4D convolution Convolutional neural network Attention mechanism}, doi={10.1007/978-3-031-55471-1_9} }- Qiuming Liu
Ruiqin Li
Ke Yan
Yichen Wang
Yong Luo
Year: 2024
An Improved 4D Convolutional Neural Network for Light Field Reconstruction
MONAMI
Springer
DOI: 10.1007/978-3-031-55471-1_9
Abstract
Light field (LF) camera sensors often face a trade-off between angular resolution and spatial resolution when shooting. High spatial resolution image arrays often result in lower angular resolution, and vice versa. In order to obtain high spatial resolution and at the same time have high angular resolution. In this paper, we propose an improved 4D convolutional neural network (CNN) algorithm for angular super-resolution (SR) to improve the quality of angular SR images. Firstly, to address the problem of low luminance of images captured by LF cameras, this paper uses block threshold square reinforcement (BTSR) for image luminance enhancement. Secondly, to make the reconstructed new viewpoints of higher quality, this paper improves the attention mechanism convolutional block attention module (CBAM). This paper incorporates it into a 4D dense residual network as high dimensional attention module (HDAM). HDAM generates images along two independent dimensions, spatial and channel. The HDAM generates attention maps along two independent dimensions, space and channel, which guide the network to focus on more important features for adaptive feature modification. Finally, this paper modifies the activation function to make the network perform better in the later stages of training and more suitable for LF reconstruction tasks. This paper evaluates the network on many LF data, including real-world scenes and synthetic data. The experimental results show that the improved network algorithm can achieve higher quality LF reconstruction.
