Timezone: »

LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond
Wenbo Li · Kun Zhou · Lu Qi · Nianjuan Jiang · Jiangbo Lu · Jiaya Jia

Mon Dec 07 09:00 PM -- 11:00 PM (PST) @ Poster Session 0 #106

Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version. Last few years have witnessed impressive progress propelled by deep learning methods. However, one critical challenge faced by existing methods is to strike a sweet spot of deep model complexity and resulting SISR quality. This paper addresses this pain point by proposing a linearly-assembled pixel-adaptive regression network (LAPAR), which casts the direct LR to HR mapping learning into a linear coefficient regression task over a dictionary of multiple predefined filter bases. Such a parametric representation renders our model highly lightweight and easy to optimize while achieving state-of-the-art results on SISR benchmarks. Moreover, based on the same idea, LAPAR is extended to tackle other restoration tasks, e.g., image denoising and JPEG image deblocking, and again, yields strong performance.

Author Information

Wenbo Li (The Chinese University of Hong Kong)
Kun Zhou (Shenzhen SmartMore Technology Co., Ltd.)
Lu Qi (The Chinese University of Hong Kong)
Nianjuan Jiang (Shenzhen SmartMore Technology Co., Ltd.)
Jiangbo Lu (Shenzhen SmartMore Technology Co., Ltd.)
Jiaya Jia (CUHK)

More from the Same Authors