Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

HIGHLY PARALLEL HEVC MOTION ESTIMATION BASED ON MULTIPLE TEMPORAL PREDICTORS AND NESTED DIAMOND SEARCH

Abstract: 

Rate-constrained motion estimation (RCME) is the most computationally intensive task of H.265/HEVC encoding. Massively parallel architectures, such as graphics processing units (GPUs), used in combination with a multi-core central processing unit (CPU), provide a promising computing platform to achieve fast encoding. However, the dependencies in deriving motion vector predictors (MVPs) prevent the parallelization of prediction units (PUs) processing at a frame level. Moreover, the conditional execution structure of typical fast search algorithms is not suitable for GPUs designed for data-intensive parallel problems. In this paper, we propose a novel highly parallel RCME method based on multiple temporal motion vector (MV) predictors and a new fast nested diamond search (NDS) algorithm well-suited for a GPU. The proposed framework provides fine-grained encoding parallelism. Experimental results show that our approach provides reduced GPU load with better BD-Rate compared to prior full search parallel methods based on a single MV predictor.

up
0 users have voted:

Comments

This is the poster that was presented to ICIP2017.

This is the poster that was presented at the ICIP 2017.

This is the poster that was presented at the ICIP 2017.

Paper Details

Authors:
Esmaeil Hojati, Jean-François Franche, Stéphane Coulombe, Carlos Vázquez
Submitted On:
26 September 2017 - 8:28am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Stéphane Coulombe
Paper Code:
MQ-PC.5
Document Year:
2017
Cite

Document Files

ICIP2017-Poster-Hojati.pdf

(50 downloads)

Subscribe

[1] Esmaeil Hojati, Jean-François Franche, Stéphane Coulombe, Carlos Vázquez, "HIGHLY PARALLEL HEVC MOTION ESTIMATION BASED ON MULTIPLE TEMPORAL PREDICTORS AND NESTED DIAMOND SEARCH", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2247. Accessed: Dec. 16, 2017.
@article{2247-17,
url = {http://sigport.org/2247},
author = {Esmaeil Hojati; Jean-François Franche; Stéphane Coulombe; Carlos Vázquez },
publisher = {IEEE SigPort},
title = {HIGHLY PARALLEL HEVC MOTION ESTIMATION BASED ON MULTIPLE TEMPORAL PREDICTORS AND NESTED DIAMOND SEARCH},
year = {2017} }
TY - EJOUR
T1 - HIGHLY PARALLEL HEVC MOTION ESTIMATION BASED ON MULTIPLE TEMPORAL PREDICTORS AND NESTED DIAMOND SEARCH
AU - Esmaeil Hojati; Jean-François Franche; Stéphane Coulombe; Carlos Vázquez
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2247
ER -
Esmaeil Hojati, Jean-François Franche, Stéphane Coulombe, Carlos Vázquez. (2017). HIGHLY PARALLEL HEVC MOTION ESTIMATION BASED ON MULTIPLE TEMPORAL PREDICTORS AND NESTED DIAMOND SEARCH. IEEE SigPort. http://sigport.org/2247
Esmaeil Hojati, Jean-François Franche, Stéphane Coulombe, Carlos Vázquez, 2017. HIGHLY PARALLEL HEVC MOTION ESTIMATION BASED ON MULTIPLE TEMPORAL PREDICTORS AND NESTED DIAMOND SEARCH. Available at: http://sigport.org/2247.
Esmaeil Hojati, Jean-François Franche, Stéphane Coulombe, Carlos Vázquez. (2017). "HIGHLY PARALLEL HEVC MOTION ESTIMATION BASED ON MULTIPLE TEMPORAL PREDICTORS AND NESTED DIAMOND SEARCH." Web.
1. Esmaeil Hojati, Jean-François Franche, Stéphane Coulombe, Carlos Vázquez. HIGHLY PARALLEL HEVC MOTION ESTIMATION BASED ON MULTIPLE TEMPORAL PREDICTORS AND NESTED DIAMOND SEARCH [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2247