کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Swin Wavelet Super Resolution

نویسندگان :

Zahra Moammeri¹ Ahmad Mahmoudi-Aznaveh²

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

تخمین کانال V2X با استفاده از CDP وفقی

الهام نادری مقدم - محمدعلی سبقتی - حسن زارعیان

Adaptive Control of Switched Nonlinear Systems with Unknown Control Directions

ٍElham Ovaysi - Marzieh Kamali

طراحی و پیاده‌سازی یک ماشین حالت محدود جهت محاسبة تابع مثلثاتی تانژانت معکوس مبتنی بر سری تیلور عقب‌رونده و با استفاده از دو واحد ضرب‌کنندة DSP48-E بر روی تراشه‌های FPGA شرکت AMD-XILINX به صورت زمان متغیر

میثم هارونی - پیام سنائی

Incentivizing Peer-to-Peer Energy Trading in Microgrids

Amir Noori - Babak Tavassoli - Alireza Fereidunian

A Band-pass Power Divider Based on Substrate Integrated Plasmonic Waveguide

Salma Mirhadi - Shamsi Soleimani

Effect of Physical Characteristics on Artiﬁcial Neural Network Error Reduction for Indoor Propagation Modeling

SeyedehMounes Eslami - Amir Ahmad Shishegar

Compact Multiband HMSIW Antenna Loaded with Complementary Split Ring Resonators

Rasol Zayer - Mohamamd Naghi Azarmanesh - Javad Nourinia - Changiz Ghobadi - Farzad Alizadeh - Bahman Mohammadi

Human Identification based on micro-Doppler images using Residual Networks

Ali Pouresmaeil - Pegah Kakvand - Mohammad Ali Sebt

Transfer Learning Based Method for Human Activity Recognition

Saeedeh Zebhi - Smt Almodarresi - Vahid Abootalebi

Improved Spectral Efficiency of RIS-aided 6G Communication using Deep Learning

Zahra Zahedi - Mehrdad Ardebilipur - Fatemeh Dehrouye

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4