.png){kind=icon}
Return
Light Field Image Super-Resolution Using Deformable Convolution
.png){kind=icon}
OA
AI
DOI：10.1109/TIP.2020.3042059.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Light field (LF) cameras can record scenes from multiple perspectives, and thus introduce beneficial angular information for image super-resolution (SR). However, it is challenging to incorporate angular information due to disparities among LF images. In this paper, we propose a deformable convolution network (i.e., LF-DFnet) to handle the disparity problem for LF image SR. Specifically, we design an angular deformable alignment module (ADAM) for feature-level alignment. Based on ADAM, we further propose a collect-and-distribute approach to perform bidirectional alignment between the center-view feature and each side-view feature. Using our approach, angular information can be well incorporated and encoded into features of each view, which benefits the SR reconstruction of all LF images. Moreover, we develop a baseline-adjustable LF dataset to evaluate SR performance under different disparity variations. Experiments on both public and our self-developed datasets have demonstrated the superiority of our method. Our LF-DFnet can generate high-resolution images with more faithful details and achieve state-of-the-art reconstruction accuracy. Besides, our LF-DFnet is more robust to disparity variations, which has not been well addressed in literature.
Keywords:
Light field
super-resolution
deformable convolution
dataset
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W
Organization
Cited Papers
ShareSaveMechanisms of salt-sensitive hypertension: role of renal medullary inducible nitric oxide synthase
PREAI
ShareSaveA positively selected mutation in the WNV 2K peptide confers resistance to superinfection exclusion in vivo.png)
Virology
OAAI
VirologyIF0
OAAIShareSaveShareSaveShareSave
View more