Light Field Image Super-Resolution with Transformers

TL;DR

This paper introduces a Transformer-based approach for light field image super-resolution, effectively capturing both angular and spatial dependencies to improve image quality with low computational cost.

Contribution

The paper proposes a novel angular and spatial Transformer framework for light field super-resolution, surpassing CNN-based methods in performance and efficiency.

Findings

Achieves superior super-resolution results on five public datasets.

Uses a small model size with low computational cost.

Demonstrates effectiveness through extensive ablation studies.

Abstract

Light field (LF) image super-resolution (SR) aims at reconstructing high-resolution LF images from their low-resolution counterparts. Although CNN-based methods have achieved remarkable performance in LF image SR, these methods cannot fully model the non-local properties of the 4D LF data. In this paper, we propose a simple but effective Transformer-based method for LF image SR. In our method, an angular Transformer is designed to incorporate complementary information among different views, and a spatial Transformer is developed to capture both local and long-range dependencies within each sub-aperture image. With the proposed angular and spatial Transformers, the beneficial information in an LF can be fully exploited and the SR performance is boosted. We validate the effectiveness of our angular and spatial Transformers through extensive ablation studies, and compare our method to recent state-of-the-art methods on five public LF datasets. Our method achieves superior SR performance with a small model size and low computational cost. Code is available at https://github.com/ZhengyuLiang24/LFT.