High-precision and lightweight small-target detection algorithm for low-cost edge intelligence

L ** (SLAM) is fundamental for intelligent mobile units to
perform diverse tasks. Recent work has shown that integrating neural rendering and SLAM …

A Comprehensive Survey on Real-Time Image Super-Resolution for IoT and Delay-Sensitive Applications.

MJ Rasool, S Ahmad, S Mardieva… - Applied Sciences …, 2025 - search.ebscohost.com
In contemporary computer vision, deep learning-based real-time single image super-
resolution approaches have gained significant attention for their ability to enhance the …

[HTML][HTML] Ancient Painting Inpainting with Regional Attention-Style Transfer and Global Context Perception

X Liu, J Wan, N Wang - Applied Sciences, 2024 - mdpi.com
Ancient paintings, as a vital component of cultural heritage, encapsulate a profound depth of
cultural significance. Over time, they often suffer from different degradation conditions …

Spatially-Adaptive Large-Kernel Network for Efficient Image Super-Resolution

X He, K Cao, T Hu, J Zhang, R Li - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
In the realm of image super-resolution (SR), efficiency on low-power devices remains a
significant challenge due to the high computational demands of current methods. In …

[HTML][HTML] Symmetric Connected U-Net with Multi-Head Self Attention (MHSA) and WGAN for Image Inpainting

Y Hou, X Ma, J Zhang, C Guo - Symmetry, 2024 - mdpi.com
This study presents a new image inpainting model based on U-Net and incorporating the
Wasserstein Generative Adversarial Network (WGAN). The model uses skip connections to …

Generation Diffusion Degradation: Simple and Efficient Design for Blind Super-Resolution

L Xu, H Zhou, Q Chen, G Li - Knowledge-Based Systems, 2024 - Elsevier
In the domain of computer vision, blind super-resolution is a key area focused on generating
high-resolution images with enhanced visual quality from low-resolution counterparts …

EdgeStereoSR: A multi-task network with transformers for stereo image super-resolution considering edge prior

A Liu, S Li, Y Chang, Y Hou - Signal Processing, 2025 - Elsevier
Recently, stereo image super-resolution methods focusing on exploring cross-view
information have been widely studied and achieved good performance. However, it is still …

CerviLearnNet: Advancing cervical cancer diagnosis with reinforcement learning-enhanced convolutional networks

S Muksimova, S Umirzakova, S Kang, Y Im Cho - Heliyon, 2024 - cell.com
Women tend to face many problems throughout their lives; cervical cancer is one of the most
dangerous diseases that they can face, and it has many negative consequences. Regular …