scholarly journals Video Denoising with Optical Flow Estimation

2018 ◽  
Vol 8 ◽  
pp. 142-166 ◽  
Author(s):  
Antoni Buades ◽  
Jose-Luis Lisani
Keyword(s):  
Optical Flow ◽  
Flow Estimation ◽  
Optical Flow Estimation ◽  
Video Denoising

Patch-Based Video Denoising With Optical Flow Estimation

2016 ◽  
Vol 25 (6) ◽  
pp. 2573-2586 ◽  
Author(s):  
Antoni Buades ◽  
Jose-Luis Lisani ◽  
Marko Miladinovic
Keyword(s):  
Optical Flow ◽  
Flow Estimation ◽  
Optical Flow Estimation ◽  
Video Denoising

scholarly journals Patch-based Video Denoising with Optical Flow Estimation

2017 ◽  
Vol 05 (04) ◽  
pp. 15-20
Author(s):  
Jaichander C ◽  
Santhoshkumar M ◽  
Vijayakumar K ◽  
Vinothkumar C ◽  
Vijayakanth V
Keyword(s):  
Optical Flow ◽  
Flow Estimation ◽  
Optical Flow Estimation ◽  
Video Denoising

Quantitative Comparative Study of Video Denoising with Optical Flow Estimation in Spatial and Transform Domains

2020 ◽  
Vol 5 (3) ◽  
pp. 159-166
Author(s):  
Sofiane KHOUDOUR ◽  
Zoubeida MESSALI ◽  
Rima BELKHITER
Keyword(s):  
Comparative Study ◽  
Optical Flow ◽  
Additive White Gaussian Noise ◽  
Video Quality ◽  
Performance Criteria ◽  
Flow Estimation ◽  
Optical Flow Estimation ◽  
Estimation Algorithms ◽  
Video Denoising

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.

scholarly journals Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow

2020 ◽  
Vol 34 (07) ◽  
pp. 10713-10720
Author(s):  
Mingyu Ding ◽  
Zhe Wang ◽  
Bolei Zhou ◽  
Jianping Shi ◽  
Zhiwu Lu ◽  
...  
Keyword(s):  
Optical Flow ◽  
Video Segmentation ◽  
Video Clip ◽  
Semantic Segmentation ◽  
Temporal Consistency ◽  
Flow Estimation ◽  
Optical Flow Estimation ◽  
Optical Flows ◽  
Benchmark Datasets ◽  
Spatio Temporal

A major challenge for video semantic segmentation is the lack of labeled data. In most benchmark datasets, only one frame of a video clip is annotated, which makes most supervised methods fail to utilize information from the rest of the frames. To exploit the spatio-temporal information in videos, many previous works use pre-computed optical flows, which encode the temporal consistency to improve the video segmentation. However, the video segmentation and optical flow estimation are still considered as two separate tasks. In this paper, we propose a novel framework for joint video semantic segmentation and optical flow estimation. Semantic segmentation brings semantic information to handle occlusion for more robust optical flow estimation, while the non-occluded optical flow provides accurate pixel-level temporal correspondences to guarantee the temporal consistency of the segmentation. Moreover, our framework is able to utilize both labeled and unlabeled frames in the video through joint training, while no additional calculation is required in inference. Extensive experiments show that the proposed model makes the video semantic segmentation and optical flow estimation benefit from each other and outperforms existing methods under the same settings in both tasks.

Sign in / Sign up

Export Citation Format

Share Document