Progressive spatial-angular feature enhancement network for light field image super-resolution |
| |
Affiliation: | 1. Science and Technology on Complex Electronic System Simulation Laboratory, Space Engineering University, Beijing 101400, China;2. Beijing Institute of Remote Sensing Information, Beijing 100192, China;3. Beihang University, Beijing 100089, China;4. Naval Aviation University, Yantai 264001, China;1. Ewha Womans University, Republic of Korea;2. Samsung Electronics, Republic of Korea;1. Orange Labs, France;2. Institut Mines-Télécom, Télécom ParisTech, CNRS LTCI, France;3. Holografika Kft., Hungary;4. Department of Signal Processing, Tampere University of Technology, Finland;5. Pazmany Peter Catholic University, Faculty of information Technology, Hungary;1. School of Computer Engineering, Nanjing Institute of Technology, Nanjing, China;2. College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, China |
| |
Abstract: | The intensity and direction of the light field (LF) can be recorded simultaneously by using LF cameras. However, since LF cameras sacrifice spatial resolution for higher angular resolution, the images acquired by LF cameras tend to have low spatial resolution. Therefore, LF image super-resolution (SR) has become an integral part of LF studies. Many existing LF image SR methods fail to fully utilize angular and spatial information due to only using partial sub-aperture images (SAIs). In this paper, we propose a progressive spatial-angular feature enhancement network (PSAFENet) to deal with the problem of missing information in LF image SR. Specifically, we first extract the spatial features of SAIs, the spatial and angular features contained in the macro-pixel images (MacPIs) by three different feature extraction modules. Then, these features are fed into a spatial-angular feature enhancement (SAFE) module to perform enhancement of spatial-angular information on the SAIs. To improve the reconstruction accuracy, we also use the information multi-distillation block (IMDB) to remove the redundant information before upsampling. Our network can well merge the angular and spatial information into each SAI, which facilitates the reconstruction of the LF images. Experimental results on five public datasets show that the proposed PSAFENet method outperforms existing methods in both qualitative and quantitative comparisons. |
| |
Keywords: | Light field Spatial super-resolution Spatial-angular information Sub-aperture images Macro-pixel images |
本文献已被 ScienceDirect 等数据库收录! |
|