Paper Info
Title
P-frame Coding Proposal by NCTU: Parametric Video Prediction through Backprop-based Motion Estimation
Abstract
This paper presents a parametric video prediction scheme with backprop-based motion estimation, in response to the CLIC challenge on P-frame compression. Recognizing that most learning-based video codecs rely on optical flow-based temporal prediction and suffer from having to signal a large amount of motion information, we propose to perform parametric overlapped block motion compensation on a sparse motion field. In forming this sparse motion field, we conduct the steepest descent algorithm on a loss function for identifying critical pixels, of which the motion vectors are communicated to the decoder. Moreover, we introduce a critical pixel dropout mechanism to strike a good balance between motion overhead and prediction quality. Compression results with HEVC-based residual coding on CLIC validation sequences show that our parametric video prediction achieves higher PSNR and MS-SSIM than optical flow-based warping. Moreover, our critical pixel dropout mechanism is found beneficial in terms of rate-distortion performance. Our scheme offers the potential for working with learned residual coding.
Year
DOI
Venue
2020
10.1109/CVPRW50498.2020.00083
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Keywords
DocType
ISSN
motion vectors,critical pixel dropout mechanism,motion overhead,prediction quality,HEVC-based residual coding,optical flow-based warping,P-frame coding proposal,backprop-based motion estimation,parametric video prediction scheme,P-frame compression,learning-based video codecs,optical flow-based temporal prediction,motion information,parametric overlapped block motion compensation,sparse motion field
Conference
2160-7508
ISBN
Citations 
PageRank 
978-1-7281-9361-8
0
0.34
References 
Authors
1
5
Name
Order
Citations
PageRank
Yung-Han Ho100.34
Chih-Chun Chan200.34
David Alexandre322.06
Wen-Hsiao Peng420933.15
Chih-Peng Chang512.06