TY - GEN
T1 - P-frame coding proposal by NCTU
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
AU - Ho, Yung Han
AU - Chan, Chih Chun
AU - Alexandre, David
AU - Peng, Wen-Hsiao
AU - Chang, Chih Peng
PY - 2020/6/14
Y1 - 2020/6/14
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85090139400&partnerID=8YFLogxK
U2 - 10.1109/CVPRW50498.2020.00083
DO - 10.1109/CVPRW50498.2020.00083
M3 - Conference contribution
AN - SCOPUS:85090139400
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 598
EP - 601
BT - Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PB - IEEE Computer Society
Y2 - 14 June 2020 through 19 June 2020
ER -