A Quantitative Comparative Study of Video Denoising with Optical Flow Estimation in Spatial and Transform Domains
Keywords:Optical flow estimation, Video denoising, Patch denoising, Transform Domain
In this paper we establish an extensive quantitative comparative study of patch-based video denoising with optical flow estimation algorithms. Namely, SPTWO, VBM3D and VBM4D algorithms are considered. The aim of this study is to combine these video denoising algorithms in a hybrid proposed process to take advantage of. SPTWO takes advantage of the self-similarity and redundancy of adjacent frames. The proposed hybrid algorithm and the three video denoising algorithms are implemented and tested on real sequences degraded by various level Additive White Gaussian Noise (AWGN). The obtained results are compared in terms of the most used performance criteria for various test cases. The performance criteria computed in this study are: RMSE and SSIM in addition to the running time and visual quality of the sequence video. Experimental results, illustrate that the proposed algorithm and SPTWO provide the best video quality and appear to be efficient in terms of preserving fine texture and detail reconstruction.
How to Cite
Copyright (c) 2020 Sofiane KHOUDOUR, Zoubeida MESSALI, Rima BELKHITER
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.