DnSwin: Toward real-world denoising via a continuous Wavelet Sliding Transformer
Real-world image denoising is a practical image restoration problem that aims to obtain
clean images from in-the-wild noisy inputs. Recently, the Vision Transformer (ViT) has …
clean images from in-the-wild noisy inputs. Recently, the Vision Transformer (ViT) has …
Reference-free low-light image enhancement by associating hierarchical wavelet representations
For computer vision and image content understanding, the low-light image becomes an
obvious challenge as it suffers from poor contrast and illumination. Hence, low-light image …
obvious challenge as it suffers from poor contrast and illumination. Hence, low-light image …
Scale-aware squeeze-and-excitation for lightweight object detection
Z Xu, X Hong, T Chen, Z Yang… - IEEE Robotics and …, 2022 - ieeexplore.ieee.org
Lightweight object detection can promote intelligent robotics to recognize surroundings
objects with limited computational resources, and thus receives increasing attention in …
objects with limited computational resources, and thus receives increasing attention in …
Perception-Driven Similarity-Clarity Tradeoff for Image Super-Resolution Quality Assessment
K Zhang, T Zhao, W Chen, Y Niu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Super-Resolution (SR) algorithms aim to enhance the resolutions of images. Massive deep-
learning-based SR techniques have emerged in recent years. In such case, a visually …
learning-based SR techniques have emerged in recent years. In such case, a visually …
Learning from multi-perception features for real-word image super-resolution
Actual image super-resolution is an extremely challenging task due to complex
degradations existing in the image. To solve this problem, two dominant methodologies …
degradations existing in the image. To solve this problem, two dominant methodologies …
A joint learning method with consistency-aware for low-resolution facial expression recognition
Existing facial expression recognition (FER) methods are mainly devoted to learning
discriminative features from high-resolution images. However, when applied to low …
discriminative features from high-resolution images. However, when applied to low …
CROSE: Low-light enhancement by CROss-SEnsor interaction for nighttime driving scenes
An increasing number of image perception models are being utilized in the field of
autonomous driving. During nighttime driving, the visual perception capabilities of a single …
autonomous driving. During nighttime driving, the visual perception capabilities of a single …
Super-Resolution Degradation Model: Converting High-Resolution Datasets to Optical Zoom Datasets
Y Hao, F Yu - IEEE Transactions on Circuits and Systems for …, 2023 - ieeexplore.ieee.org
Despite remarkable progress in single-image super-resolution based on neural networks,
the results are not ideal when applied to real-world images, because the real-world …
the results are not ideal when applied to real-world images, because the real-world …
Deep Compressed Video Super-Resolution With Guidance of Coding Priors
Q Zhu, F Chen, Y Liu, S Zhu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Compressed video super-resolution (VSR) is employed to generate high-resolution (HR)
videos from low-resolution (LR) compressed videos. Recently, some compressed VSR …
videos from low-resolution (LR) compressed videos. Recently, some compressed VSR …
IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images
M Wang, Y Song, P Wei, X Xian… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep learning technologies have demonstrated their effectiveness in removing cloud cover
from optical remote-sensing images. Convolutional neural networks (CNNs) exert …
from optical remote-sensing images. Convolutional neural networks (CNNs) exert …