Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Article number | 8423122 |
Pages (from-to) | 1403-1407 |
Journal / Publication | IEEE Signal Processing Letters |
Volume | 25 |
Issue number | 9 |
Online published | 31 Jul 2018 |
Publication status | Published - Sep 2018 |
Link(s)
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.
Research Area(s)
- anisotropic parallax feature, Cameras, convolutional neural networks (CNN), denoising, Feature extraction, Light field (LF), Low-frequency noise, Noise measurement, Noise reduction, Training
Citation Format(s)
Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework. / Chen, Jie ; Hou, Junhui; Chau, Lap-Pui.
In: IEEE Signal Processing Letters, Vol. 25, No. 9, 8423122, 09.2018, p. 1403-1407.Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review