Multi-Dimension Fusion Network for Light Field Spatial Super-Resolution using Dynamic Filters

08/26/2020
by   Qingyan Sun, et al.
0

Light field cameras have been proved to be powerful tools for 3D reconstruction and virtual reality applications. However, the limited resolution of light field images brings a lot of difficulties for further information display and extraction. In this paper, we introduce a novel learning-based framework to improve the spatial resolution of light fields. First, features from different dimensions are parallelly extracted and fused together in our multi-dimension fusion architecture. These features are then used to generate dynamic filters, which extract subpixel information from micro-lens images and also implicitly consider the disparity information. Finally, more high-frequency details learned in the residual branch are added to the upsampled images and the final super-resolved light fields are obtained. Experimental results show that the proposed method uses fewer parameters but achieves better performances than other state-of-the-art methods in various kinds of datasets. Our reconstructed images also show sharp details and distinct lines in both sub-aperture images and epipolar plane images.

READ FULL TEXT

page 2

page 8

page 12

page 14

research
09/27/2017

Light field super resolution through controlled micro-shifts of light field sensor

Light field cameras presents new capabilities, such as post-capture refo...
research
10/03/2019

High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction

We consider the problem of high-dimensional light field reconstruction a...
research
03/11/2021

A learning-based view extrapolation method for axial super-resolution

Axial light field resolution refers to the ability to distinguish featur...
research
01/12/2018

Light Field Super-Resolution using a Low-Rank Prior and Deep Convolutional Neural Networks

Light field imaging has recently known a regain of interest due to the a...
research
02/22/2022

Disentangling Light Fields for Super-Resolution and Disparity Estimation

Light field (LF) cameras record both intensity and directions of light r...
research
07/05/2021

LightFuse: Lightweight CNN based Dual-exposure Fusion

Deep convolutional neural networks (DCNN) aided high dynamic range (HDR)...
research
11/17/2018

VommaNet: an End-to-End Network for Disparity Estimation from Reflective and Texture-less Light Field Images

The precise combination of image sensor and micro-lens array enables len...

Please sign up or login with your details

Forgot password? Click here to reset