Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework

TL;DR

This paper introduces a novel light field denoising method using anisotropic parallax analysis within a CNN framework, significantly improving visual quality and detail preservation over existing techniques.

Contribution

The work presents a new anisotropic parallax analysis approach combined with two CNNs for effective light field denoising, capturing high-frequency perspective details and non-Lambertian variations.

Findings

Outperforms state-of-the-art denoising methods in visual quality

Effectively preserves parallax details in noisy light fields

Enhances restoration of non-Lambertian surface variations

Abstract

Light field (LF) cameras provide perspective information of scenes by taking directional measurements of the focusing light rays. The raw outputs are usually dark with additive camera noise, which impedes subsequent processing and applications. We propose a novel LF denoising framework based on anisotropic parallax analysis (APA). Two convolutional neural networks are jointly designed for the task: first, the structural parallax synthesis network predicts the parallax details for the entire LF based on a set of anisotropic parallax features. These novel features can efficiently capture the high frequency perspective components of a LF from noisy observations. Second, the view-dependent detail compensation network restores non-Lambertian variation to each LF view by involving view-specific spatial energies. Extensive experiments show that the proposed APA LF denoiser provides a much better denoising performance than state-of-the-art methods in terms of visual quality and in preservation of parallax details.