High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction

TL;DR

This paper introduces a novel learning-based framework for high-dimensional light field reconstruction that employs 4D convolution and tensor restoration, effectively handling non-Lambertian surfaces and occlusions with improved accuracy and efficiency.

Contribution

The paper proposes a two-stage 4D convolutional neural network for light field super-resolution, incorporating a new normalization, stage-wise loss, and multi-range training for enhanced geometric feature learning.

Findings

Achieves superior reconstruction quality on diverse datasets.

Reduces execution time compared to state-of-the-art methods.

Effectively handles occlusions and non-Lambertian surfaces.

Abstract

We consider the problem of high-dimensional light field reconstruction and develop a learning-based framework for spatial and angular super-resolution. Many current approaches either require disparity clues or restore the spatial and angular details separately. Such methods have difficulties with non-Lambertian surfaces or occlusions. In contrast, we formulate light field super-resolution (LFSR) as tensor restoration and develop a learning framework based on a two-stage restoration with 4-dimensional (4D) convolution. This allows our model to learn the features capturing the geometry information encoded in multiple adjacent views. Such geometric features vary near the occlusion regions and indicate the foreground object border. To train a feasible network, we propose a novel normalization operation based on a group of views in the feature maps, design a stage-wise loss function, and develop the multi-range training strategy to further improve the performance. Evaluations are conducted on a number of light field datasets including real-world scenes, synthetic data, and microscope light fields. The proposed method achieves superior performance and less execution time comparing with other state-of-the-art schemes.