Learning Light Field Angular Super-Resolution via a Geometry-Aware Network

Jing JIN, Junhui HOU, Hui YUAN, Sam KWONG

Research output: Journal PublicationsJournal Article (refereed)peer-review

79 Citations (Scopus)


The acquisition of light field images with high angular resolution is costly. Although many methods have been proposed to improve the angular resolution of a sparsely-sampled light field, they always focus on the light field with a small baseline, which is captured by a consumer light field camera. By making full use of the intrinsic geometry information of light fields, in this paper we propose an end-to-end learning-based approach aiming at angularly super-resolving a sparsely-sampled light field with a large baseline. Our model consists of two learnable modules and a physically-based module. Specifically, it includes a depth estimation module for explicitly modeling the scene geometry, a physically-based warping for novel views synthesis, and a light field blending module specifically designed for light field reconstruction. Moreover, we introduce a novel loss function to promote the preservation of the light field parallax structure. Experimental results over various light field datasets including large baseline light field images demonstrate the significant superiority of our method when compared with state-of-the-art ones, i.e., our method improves the PSNR of the second best method up to 2 dB in average, while saves the execution time 48×. In addition, our method preserves the light field parallax structure better.
Original languageEnglish
Pages (from-to)11141-11148
JournalProceedings of the AAAI Conference on Artificial Intelligence
Issue number7
Publication statusPublished - 3 Apr 2020
Externally publishedYes
Event34th AAAI Conference on Artificial Intelligence (AAAI-20) - , United States
Duration: 7 Feb 202012 Feb 2020

Bibliographical note

This work was supported in part by the Hong Kong RGC Early Career Scheme under Grant 9048123 (CityU 21211518), and in part by the Huawei Innovative Research Program under Grant 9231332.


Dive into the research topics of 'Learning Light Field Angular Super-Resolution via a Geometry-Aware Network'. Together they form a unique fingerprint.

Cite this