Light Field Image Super-Resolution Using Deformable Convolution

TL;DR

This paper introduces LF-DFnet, a deformable convolution network that effectively incorporates angular information from light field images for super-resolution, handling disparities and improving detail fidelity.

Contribution

The paper proposes a novel angular deformable alignment module and a bidirectional collect-and-distribute approach for better disparity handling in light field super-resolution.

Findings

Achieves state-of-the-art super-resolution accuracy.

More robust to disparity variations than previous methods.

Generates high-resolution images with faithful details.

Abstract

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.