0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
Swin Wavelet Super Resolution
نویسندگان :
Zahra Moammeri
1
Ahmad Mahmoudi-Aznaveh
2
1- دانشگاه شهید بهشتی
2- دانشگاه شهید بهشتی
کلمات کلیدی :
super-resolution،transformers،wavelet transform،transform domain
چکیده :
Super Resolution has improved considerably by introducing novel approaches in the past few years. Transformers, with their abilities to capture long-range dependencies, are promising tools for super-resolution tasks. However, they suffer from the limitations of constrained patch areas. Since they process and analyze patches separately, achieving a wide and effective receptive field remains a challenge in these networks. In this work, we propose SwinWSR, a novel transformer-based model with a Spatial Wavelet block to capture more effective features through multi-scale wavelet transforms. We primarily focus on repetitive textures, such as those in the Urban100 dataset, which are particularly challenging to restore. Experimental results demonstrate that our model achieves competitive performance compared to existing methods, both quantitatively and qualitatively.
لیست مقالات
لیست مقالات بایگانی شده
Family of Multifunctional Controllable Converters for Grid, Battery, and PV-Powered EV Charging Station Applications
Homayon Soltani Gohari - Amir Safaeinasab - Karim Abbaszadeh
Wideband and Multi-band Frequency Selective Surfaces for Microwave Shielding
Mahmoodreza Marzban - Abbas Alighanbari
ANOVA-based assessment of the model-free adaptive controllers tuning parameters
Sepideh Nasrollahi - Ali Khaki-Sedigh
Single- and Multi-Hop BERT Question Classifier for Open-Domain Question Answering (SiMQC)
Faeze Zakaryapour Sayyad - Mahdi Bohlouli
Optimal Energy Management of EVs in intelligent parking lots with Considering solar panels
Noorallah Yavari - Fatemeh Jahanbani Ardakani - Alireza Sedighi Anaraki
Comparison of the MRT and ZF Precoding in Massive MIMO Systems from Energy Efficiency Viewpoint
Mahdi Nangir - Abdolrasoul Sakhaei Gharagezlou - Nima Imani
Transfer Learning Based Method for Human Activity Recognition
Saeedeh Zebhi - Smt Almodarresi - Vahid Abootalebi
کنترل تطبیقی بازوی رباتی دو درجه آزادی با استفاده از یادگیری گروهی مبتنیبر الگوریتم اکثریت وزندار شده تصادفی
علی چراغی - امیرحسین جراره - سعید شمقدری
A Geometry-based Approach to Reduce the Quantization lobe in 1-bit Reconfigurable Intelligent Surfaces
Nima Ahmadi - Forouhar Farzaneh
سیستم تشخیص فعالیت مبتنی بر مدلسازی تصویری تنک اطلاعات حالت کانال و شبکه عصبی کانولوشنی
علیرضا ابوالقاسمی - سید محمد تقی المدرسی - سید مجتبی آقایی
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 41.7.4