Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework

05/31/2018
by   Jie Chen, et al.
0

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.

READ FULL TEXT

page 1

page 3

page 4

research
08/16/2018

A Pipeline for Lenslet Light Field Quality Enhancement

In recent years, light fields have become a major research topic and the...
research
09/09/2016

Learning-Based View Synthesis for Light Field Cameras

With the introduction of consumer light field cameras, light field imagi...
research
08/09/2023

WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields

Neural Radiance Field (NeRF) has shown impressive performance in novel v...
research
05/05/2023

Contrastive Learning for Low-light Raw Denoising

Image/video denoising in low-light scenes is an extremely challenging pr...
research
03/17/2020

Burst Denoising of Dark Images

Capturing images under extremely low-light conditions poses significant ...
research
08/15/2020

Evolving Deep Convolutional Neural Networks for Hyperspectral Image Denoising

Hyperspectral images (HSIs) are susceptible to various noise factors lea...
research
07/31/2023

Towards General Low-Light Raw Noise Synthesis and Modeling

Modeling and synthesizing low-light raw noise is a fundamental problem f...

Please sign up or login with your details

Forgot password? Click here to reset