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

RDOD: A Robust Distance-based Technique for Outlier Detection

Reza Heydari gharaei - Hossein Nezamabadi-pour

MODELING AGE-RELATED CHANGES IN VISUAL EVOKED RESPONSES USING CORRELATION METRICS AND INTER-ELECTRODE CONNECTIVITY

Seyyed Saleh Fazaeli Hashemi - Farveh Daneshvarfard - Nasrin Maarefi

Fast and Low Power Modified Carry Look-Ahead Adder

Sanaz Salem - Amir hossein Owji

Decoding Trait: Using Dual Transformers to Analyze Gender, Age Range and Personality

ُSaeed Asadian - Mostafa Tanasan - Bijan Vosoughi vahdat

Large Scale Indoor VLC Positioning Using Image Sensor with Limited Field of View

Arezoo Kabiri - Foroogh Sadat Tabataba

Joint Energy and Throughput Optimization in Energy Harvesting Cognitive Sensor Networks

Morteza Sharifi - Mahmood Mohassel Feghhi

Design of a High-Efficiency Balanced Power Amplifier with 68% Fractional Bandwidth

Fatemeh Mohabati - Marzieh Chegini - Mahmoud Kamarei

کنترل فرآیند سیستم های حرارتی بر اساس مدل دو بعدیFMM و رویکرد یادگیری تکرارشونده تطبیقی

سهیلا عابدی - طاهره بینازاده

بهبود بازدهی انرژی در اینترنت اشیاء باند باریک با وفقی‌سازی لینک به کمک یادگیری عمیق

سمانه امیریان - محمدعلی سبقتی

بهبود تخصیص منابع لبه‌ها در شبکه LTE مبتنی بر محاسبات لبه با رویکرد تعادل میان تاخیر و قابلیت اطمینان

ایمان عظیمی احمدآبادی - علی اکبر تدین تفت

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2