Random shuffle transformer for image restoration

J **ao, X Fu, M Zhou, H Liu… - … Conference on Machine …, 2023 - proceedings.mlr.press
Non-local interactions play a vital role in boosting performance for image restoration.
However, local window Transformer has been preferred due to its efficiency for processing …

AverNet: All-in-one video restoration for time-varying unknown degradations

H Zhao, L Tian, X **ao, P Hu… - Advances in Neural …, 2025 - proceedings.neurips.cc
Traditional video restoration approaches were designed to recover clean videos from a
specific type of degradation, making them ineffective in handling multiple unknown types of …

VRetouchEr: Learning Cross-frame Feature Interdependence with Imperfection Flow for Face Retouching in Videos

W Xue, L Jiang, L **e, S Wu, Y Xu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Face Video Retouching is a complex task that often requires labor-intensive manual
editing. Conventional image retouching methods perform less satisfactorily in terms of …

Region-Aware Sequence-to-Sequence Learning for Hyperspectral Denoising

J **ao, Y Liu, X Wei - European Conference on Computer Vision, 2024 - Springer
Proper spectral modeling within hyperspectral image (HSI) is critical yet highly challenging
for HSI denoising. In contrast to existing methods that struggle between effectiveness and …

Image deblurring method based on self-attention and residual wavelet transform

B Zhang, J Sun, F Sun, F Wang, B Zhu - Expert Systems with Applications, 2024 - Elsevier
The restoration technology of non-uniform blurred images is a challenging open topic. Most
of the existing algorithms fail to effectively fuse multi-scale feature extraction with a self …

Rethinking prediction-based video anomaly detection from local–global normality perspective

M Zhao, X Zeng, Y Liu, J Liu, C Pang - Expert Systems with Applications, 2025 - Elsevier
Video anomaly detection (VAD) has been intensively studied for years because of its
potential applications in intelligent video systems. Prediction-based VAD methods have …

Attentive Large Kernel Network with Mixture of Experts for Video Deblurring

C Zhang, R **ong, X Fan, D Zhao - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Video deblurring is a fundamental problem in low-level vision, and many methods have
employed designs based on CNNs and transformers. Traditional CNNs often require deeper …

An implicit alignment for video super-resolution

K Xu, Z Yu, X Wang, MB Mi, A Yao - arxiv preprint arxiv:2305.00163, 2023 - arxiv.org
Video super-resolution commonly uses a frame-wise alignment to support the propagation
of information over time. The role of alignment is well-studied for low-level enhancement in …

EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

D Kai, J Lu, Y Zhang, X Sun - arxiv preprint arxiv:2406.13457, 2024 - arxiv.org
Event-based vision has drawn increasing attention due to its unique characteristics, such as
high temporal resolution and high dynamic range. It has been used in video super …

Memory-based gradient-guided progressive propagation network for video deblurring

G Song, S Gai, F Da - The Visual Computer, 2024 - Springer
Video deblurring is a challenging visual task because it requires handling temporal
correlations among frames and dealing with various sources of uncertainty in motion blur. To …