REVISTA
AI

   
Redirigiendo al acceso original de articulo en 21 segundos...
Inicio  /  AI  /  Vol: 4 Par: 3 (2023)  /  Artículo
ARTÍCULO
TITULO

Evaluating Deep Learning Techniques for Blind Image Super-Resolution within a High-Scale Multi-Domain Perspective

Valdivino Alexandre de Santiago Júnior    

Resumen

Despite several solutions and experiments have been conducted recently addressing image super-resolution (SR), boosted by deep learning (DL), they do not usually design evaluations with high scaling factors. Moreover, the datasets are generally benchmarks which do not truly encompass significant diversity of domains to proper evaluate the techniques. It is also interesting to remark that blind SR is attractive for real-world scenarios since it is based on the idea that the degradation process is unknown, and, hence, techniques in this context rely basically on low-resolution (LR) images. In this article, we present a high-scale (8×) experiment which evaluates five recent DL techniques tailored for blind image SR: Adaptive Pseudo Augmentation (APA), Blind Image SR with Spatially Variant Degradations (BlindSR), Deep Alternating Network (DAN), FastGAN, and Mixture of Experts Super-Resolution (MoESR). We consider 14 datasets from five different broader domains (Aerial, Fauna, Flora, Medical, and Satellite), and another remark is that some of the DL approaches were designed for single-image SR but others not. Based on two no-reference metrics, NIQE and the transformer-based MANIQA score, MoESR can be regarded as the best solution although the perceptual quality of the created high-resolution (HR) images of all the techniques still needs to improve.

 Artículos similares

       
 
Taesik Kim, Ho Choi, Jinman Jung, Hong Min and Young-Hoon Jung    
The terrestrial photogrammetry technique provides an efficient and accurate solution for evaluating ground deformations induced by construction activities.
Revista: Applied Sciences

 
Majed A. Alshamari    
Social media has become common as a means to convey opinions and express the extent of satisfaction and dissatisfaction with a service or product. In the Kingdom of Saudi Arabia specifically, most social media users share positive and negative opinions a... ver más
Revista: Computers

 
Lu Zhang, Hongyu Yang and Xiping Wu    
Air traffic management (ATM) relies on the running condition of the air traffic control sector (ATCS), and assessing whether it is overloaded is crucial for efficiency and safety for the entire aviation industry. Previous approaches to evaluating air tra... ver más
Revista: Aerospace

 
Firozeh Solimani, Angelo Cardellicchio, Massimiliano Nitti, Alfred Lako, Giovanni Dimauro and Vito Renò    
Plant phenotyping studies the complex characteristics of plants, with the aim of evaluating and assessing their condition and finding better exemplars. Recently, a new branch emerged in the phenotyping field, namely, high-throughput phenotyping (HTP). Sp... ver más
Revista: Information

 
Ya-Sin Yang, Hsin-Fu Yeh, Chia-Chi Huang and Hsin-Yu Chen    
Owing to active orogenic movement and the monsoon climate, rainfall-induced landslide disasters often occur in Taiwan. Hence, hillslope hydrology and stability have received considerable research attention. However, it remains difficult to accurately est... ver más
Revista: Water