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 …
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.
In contemporary computer vision, deep learning-based real-time single image super-
resolution approaches have gained significant attention for their ability to enhance the …
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 …
cultural significance. Over time, they often suffer from different degradation conditions …
Spatially-Adaptive Large-Kernel Network for Efficient Image Super-Resolution
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 …
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 …
Wasserstein Generative Adversarial Network (WGAN). The model uses skip connections to …
Generation Diffusion Degradation: Simple and Efficient Design for Blind Super-Resolution
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 …
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 …
information have been widely studied and achieved good performance. However, it is still …
CerviLearnNet: Advancing cervical cancer diagnosis with reinforcement learning-enhanced convolutional networks
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 …
dangerous diseases that they can face, and it has many negative consequences. Regular …