Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework

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.

References in corpus (4)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Learning-Based View Synthesis for Light Field Cameras
• Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions
• Light Field Compression with Disparity Guided Sparse Coding based on Structural Key Views

Cited by in corpus (5)

• Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration
• Deep Learning on Image Denoising: An overview
• Probabilistic-based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoising
• Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization
• Light Field Super-resolution via Attention-Guided Fusion of Hybrid Lenses