Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines

TL;DR

This paper introduces a learnable dynamic interpolation method for reconstructing dense light fields from sparse, wide-baseline inputs, outperforming existing techniques in quality and structure preservation.

Contribution

It proposes a novel neural network-based dynamic interpolation approach that replaces traditional geometry warping for better adaptation to content and view variations in light field reconstruction.

Findings

Achieves higher PSNR and SSIM than state-of-the-art methods.

Better preserves light field parallax structure.

Effective in wide-baseline, sparse light field scenarios.

Abstract

In this paper, we tackle the problem of dense light field (LF) reconstruction from sparsely-sampled ones with wide baselines and propose a learnable model, namely dynamic interpolation, to replace the commonly-used geometry warping operation. Specifically, with the estimated geometric relation between input views, we first construct a lightweight neural network to dynamically learn weights for interpolating neighbouring pixels from input views to synthesize each pixel of novel views independently. In contrast to the fixed and content-independent weights employed in the geometry warping operation, the learned interpolation weights implicitly incorporate the correspondences between the source and novel views and adapt to different image content information. Then, we recover the spatial correlation between the independently synthesized pixels of each novel view by referring to that of input views using a geometry-based spatial refinement module. We also constrain the angular correlation between the novel views through a disparity-oriented LF structure loss. Experimental results on LF datasets with wide baselines show that the reconstructed LFs achieve much higher PSNR/SSIM and preserve the LF parallax structure better than state-of-the-art methods. The source code is publicly available at https://github.com/MantangGuo/DI4SLF.