Multicontrast MRI Super-Resolution via Transformer-Empowered Multiscale Contextual Matching and Aggregation

Lyu, Jun; Li, Guangyuan; Wang, Chengyan; Cai, Qing; Dou, Qi; Zhang, David; Qin, Jing

doi:10.1109/tnnls.2023.3250491

Cited by 10 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image super-resolution (SR) is a technique that aims to recover high-resolution (HR) image from its corresponding degraded low-resolution (LR) version with algorithms alone, without the need for any hardware device. It plays an important and fundamental role in many computer vision tasks (Haris, Shakhnarovich, and Ukita 2018;Zhang et al 2021;Xia et al 2022;Cao et al 2016;Cai et al 2023;Lyu et al 2023). Due to their superior feature representation capabilities, convolutional neural networks (CNNs) have achieved remarkable success in SR and many architectures have been presented so far, for example, residual learning (Kim, Lee, and Lee 2016;Nie et al 2020)…”

Section: Introductionmentioning

confidence: 99%

Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution

Cai,

Li,

Ren

et al. 2024

AAAI

View full text Add to dashboard Cite

Omnidirectional images have attracted significant attention in recent years due to the rapid development of virtual reality technologies. Equirectangular projection (ERP), a naive form to store and transfer omnidirectional images, however, is challenging for existing two-dimensional (2D) image super-resolution (SR) methods due to its inhomogeneous distributed sampling density and distortion across latitude. In this paper, we make one of the first attempts to design a spherical pseudo-cylindrical representation, which not only allows pixels at different latitudes to adaptively adopt the best distinct sampling density but also is model-agnostic to most off-the-shelf SR methods, enhancing their performances. Specifically, we start by upsampling each latitude of the input ERP image and design a computationally tractable optimization algorithm to adaptively obtain a (sub)-optimal sampling density for each latitude of the ERP image. Addressing the distortion of ERP, we introduce a new viewport-based training loss based on the original 3D sphere format of the omnidirectional image, which inherently lacks distortion. Finally, we present a simple yet effective recursive progressive omnidirectional SR network to showcase the feasibility of our idea. The experimental results on public datasets demonstrate the effectiveness of the proposed method as well as the consistently superior performance of our method over most state-of-the-art methods both quantitatively and qualitatively.

show abstract