Hierarchically aggregated residual transformation for single image super resolution

Zejiang Hou, Sun Yuan Kung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Visual patterns usually appear at different scales/sizes in natural images. Multi-scale feature representation is of great importance for the single-image super-resolution (SISR) task to reconstruct image objects at different scales. However, such characteristic has been rarely considered by CNN-based SISR methods. In this work, we propose a novel building block, i.e. hierarchically aggregated residual transformation (HART), to achieve multi-scale feature representation in each layer of the network. Within each HART block, we connect multiple convolutions in a hierarchical residual-like manner, which efficiently provides a wide range of effective receptive fields at a more granular level to detect both local and global image features. To theoretically understand the proposed HART block, we recast SISR as an optimal control problem and show that HART effectively approximates the classical 4th-order Runge-Kutta method, which has the merit of small local truncation error for solving numerical ordinary differential equation. By cascading the proposed HART blocks, we establish our high-performing HARTnet. Through extensive experiments on various benchmark datasets under different degradation models, we demonstrate that HARTnet compares favourably against existing state-of-the-art methods (including those in the NTIRE 2019 SR Challenge leaderboard) in terms of both quantitative metrics and visual quality. Moreover, the same HARTnet architecture achieves promising performance on such other image restoration tasks as image denoising and low-light image enhancement.

Original languageEnglish (US)
Title of host publicationProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2248-2255
Number of pages8
ISBN (Electronic)9781728188089
DOIs
StatePublished - 2020
Event25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, Italy
Duration: Jan 10 2021Jan 15 2021

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference25th International Conference on Pattern Recognition, ICPR 2020
Country/TerritoryItaly
CityVirtual, Milan
Period1/10/211/15/21

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Hierarchically aggregated residual transformation for single image super resolution'. Together they form a unique fingerprint.

Cite this