FMPN : Fusing Multiple Progressive CNNs for Depth Map Super-Resolution

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)170754-170768
Journal / PublicationIEEE Access
Volume8
Online published18 Sep 2020
Publication statusPublished - 2020

Link(s)

Abstract

The Convolution Neural Network (CNN) is widely used in the super-resolution task of depth map. However, the ones with simple architecture and high efficiency generally lack accuracy, while the ones with high accuracy demonstrate low efficiency and training difficulties due to their over-deep level and complex architecture. We propose a depth map super-resolution fusion framework. This framework fuses multiple Progressive Convolution Neural Networks (PCNNs) with different architectures by a pixel-wise Partial Differential Equation (PDE). Each individual PCNN uses progressive learning and deep supervising to construct a mapping from low resolution space to high resolution space. The PDE model automatically classifies and processes the high-resolution depth maps with different feature output by fusing multiple PCNNs. The fusion term in PDE is used to preserve or integrate the complementary features of the depth maps, and the divergence term in PDE is used to remove noise to improve the spatial accuracy and visual effect of the final output depth map. This method enables simple structured Neural Networks with high accuracy, high efficiency and relatively simple network training for depth map super-resolution.

Research Area(s)

  • Neural networks, Convolution, Spatial resolution, Training, Mathematical model, Fuses, Depth map super-resolution, progressive convolution neural network, partial differential equation, fusion network, ENHANCEMENT

Citation Format(s)

FMPN : Fusing Multiple Progressive CNNs for Depth Map Super-Resolution. / LI, Shuaihao; ZHANG, Bin; ZHU, Weiping; YANG, Xinfeng.

In: IEEE Access, Vol. 8, 2020, p. 170754-170768.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

Download Statistics

No data available