“Super Resolution for Humans” by Karpenko, Tariq, Condor and Didyk
Conference:
Type(s):
Title:
- Super Resolution for Humans
Session/Category Title:
- Images, Video & Computer Vision
Presenter(s)/Author(s):
Abstract:
We introduce an architecture-agnostic super-resolution framework that uses human visual sensitivity to allocate computational resources efficiently, delivering substantial reductions in computational demand without perceptible quality loss, as validated by user studies—offering significant advantages for applications like VR and AR.
References:
[1] Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee. 2016. Accurate Image Super-Resolution Using Very Deep Convolutional Networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), 1646–1654.
[2] Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, and Kyoung Mu Lee. 2017. Enhanced Deep Residual Networks for Single Image Super-Resolution. arxiv:https://arXiv.org/abs/1707.02921 [cs.CV] https://arxiv.org/abs/1707.02921
[3] Rafał K. Mantiuk, Maliha Ashraf, and Alexandre Chapiro. 2022. stelaCSF: a unified model of contrast sensitivity as the function of spatio-temporal frequency, eccentricity, luminance and area. 41, 4 (2022).
[4] O. Tursun, Elena Arabadzhiyska-Koleva, Marek Wernikowski, Radosław Mantiuk, Hans-Peter Seidel, Karol Myszkowski, and Piotr Didyk. 2019. Luminance-contrast-aware foveated rendering. SIGGRAPH (2019).
