Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
This addresses noise in light field cameras for applications like 3D imaging, but it is incremental as it builds on existing CNN methods.
The paper tackles light field denoising by proposing a framework using anisotropic parallax analysis with two CNNs, resulting in better denoising performance than state-of-the-art methods in visual quality and parallax detail preservation.
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.