0% Complete
فارسی
Home
/
دوازدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
A perceptual loss for screen content image super-resolution
Authors :
Hossein Sekhavaty-Moghadam
1
Marzieh Hosseinkhani
2
Azadeh Mansouri
3
1- خوارزمی تهران
2- خوارزمی تهران
3- خوارزمی تهران
Keywords :
single image super-resolution, deep learning, neural networks, loss function, screen content images
Abstract :
The acceptable results of deep learning led to the use of the deep neural network on a wide range of models, including image super-resolution. The performance of the deep neural network is directly affected by its loss function. Most methods use intensity loss, such as MSE, which computes the difference between the predicted image and the ground truth. Since the human visual system is more sensitive to the structural information of the scene, it is desired that the loss function could measure the impact of the structural error. The use of screen content images has become widespread because of many applications such as desktop-sharing and remote computing. As a result, super-resolution of screen content images becomes a crucial technique to enhance the quality of low-resolution images. In the presented loss function, the structural error is weighted employing DCT components. The model is trained and tested using the screen content images, and the experimental subjective and objective results illustrate the effectiveness of the presented loss for screen content images.
Papers List
List of archived papers
یک رویکرد سریع تحلیل و شناسایی آسیب پذیری Next-Intent در برنامه های کاربردی اندروید
زهرا کلوندی - دکتر مهدی سخائی نیا زهرا کلوندی - مهدی سخائی نیا -
A Biased Random Key Genetic Algorithm for the Dial-a-Ride Problem
ُSomayeh Sohrabi - Koorush Ziarati - Morteza Keshtkaran
حفظ حریم خصوصی در انتشار نسخه های متوالی دادههای شبکه اجتماعی با امکان افزایش یال
طاهره سرزهی - دکتر مهری رجایی طاهره سرزهی - مهری رجایی -
Predicting Suicide Risk in Adolescents with Random Forest for Unbalanced Data Management
Fatemeh Rabbani - Dr Behrooz Masoumi - Dr Mohammad Reza Keyvanpour
Movable Antenna Design for UAV-Aided Federated Learning via Deep Reinforcement Learning
MOHSEN Ahmadzadeh - Saeid Pakravan - Ghosheh Abed Hodtani
A qualitative spoofing detection system based on LSTMs for IoMT
Iman Jafarian - Amirmasoud Sepehrian - Siavash Khorsandi
دستهبندی متون خبری فارسی با یادگیری فعال
مینا طباطبائی - دکتر سعیده ممتازی
Benchmarking Embedding Models for Persian-Language Semantic Information Retrieval
Mahmood Kalantari - Mehdi Feghhi - Nasser Mozayani
Leveraging Retrieval-Augmented Generation for Persian University Knowledge Retrieval
Arshia Hemmat - Mohammad Hassan Heydari - Kianoosh Vadaei - Afsaneh Fatemi
Statistical Disorder Parameters Computing For Hyperspectral Image Anomaly Detection
Dr Maryam Imani
more
Samin Hamayesh - Version 41.3.1