Edge-guided second-order total generalized variation for Gaussian noise removal from depth map

Shuaihao Li,Weiping Zhu,Xinfeng Yang,Bin Zhang

doi:10.1038/s41598-020-73342-3

Abstract

Total generalized variation models have recently demonstrated high-quality denoising capacity for single image. In this paper, we present an accurate denoising method for depth map. Our method uses a weighted second-order total generalized variational model for Gaussian noise removal. By fusing an edge indicator function into the regularization term of the second-order total generalized variational model to guide the diffusion of gradients, our method aims to use the first or second derivative to enhance the intensity of the diffusion tensor. We use the first-order primal–dual algorithm to minimize the proposed energy function and achieve high-quality denoising and edge preserving result for depth maps with high -intensity noise. Extensive quantitative and qualitative evaluations in comparison to bench-mark datasets show that the proposed method provides significant higher accuracy and visual improvements than many state-of-the-art denoising algorithms.

Highlights

Total generalized variation models have recently demonstrated high-quality denoising capacity for single image
We have presented an edge-guided second-order total generalized variation for Gaussian noise removal from depth map (ESTGV)
In order to solve the edge blurring issue during denoising depth maps with high-intensity Gaussian noise, we propose an edge-guided second-order total generalized variation model (ESTGV) for depth map Gaussian noise removal

Summary

Introduction

Total generalized variation models have recently demonstrated high-quality denoising capacity for single image. By fusing an edge indicator function into the regularization term of the second-order total generalized variational model to guide the diffusion of gradients, our method aims to use the first or second derivative to enhance the intensity of the diffusion tensor. We use the first-order primal–dual algorithm to minimize the proposed energy function and achieve high-quality denoising and edge preserving result for depth maps with high -intensity noise. The deep learning-based methods have recently demonstrated high-quality denoising for various images. Such methods have some drawbacks, such as, the optimization of network structure requires a lot of training, and the datasets required for training are often very large. Specific models need to be trained for specific noise intensity, so their application universality is still poor

Objectives

Methods

Results

Conclusion