110 likes | 351 Views
Training-based Super Resolution Enhancement using CUDA. D99922013 張書豪 R99944018 張嫚家 R99944035 楊逸民. Outline. Introduction Training-based super resolution method Improvement and application Task and Goal Schedule. Introduction. Super resolution can enhance the resolution of images
E N D
Training-based Super Resolution Enhancement using CUDA D99922013 張書豪 R99944018 張嫚家 R99944035 楊逸民
Outline • Introduction • Training-based super resolution method • Improvement and application • Task and Goal • Schedule
Introduction • Super resolution can enhance the resolution of images • Image upsampling
Introduction • Related work • thumbnail image • low resolution image -> high resolution image • Make better quality • surveillance system • online video quality
Introduction • Motivation • SR is useful in generating high resolution images • Yet very time-consuming
Original method • Background • Hong Chang, Dit-Yan Yeung, YiminXiong, “Super Resolution through Neighbor Embedding,” CVPR 2004 • Training-based super resolution • Multiple training patches from different images • Preserve the low resolution and high resolution correspondence
Improvement • Pre-processing • compute energy map to separate low and high frequency region • LR patches can be parallelly processed • compute LR feature vector • K-NN search • weight vector • HR patch composition
Tasks and Goals • Get high resolution images in short time • Extend super resolution to video sequences • Example • youtube video sequences • Fast loading on high resolution video such as 480p, 720p
Schedule • In project midterm • Finish image super resolution on CUDA one month later • In project final • Finish video super resolution on CUDA