54 citations · 131 across the 84 of their papers we have counts for
7 papers · 1 filter
Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation
Xin Yang, Xiaogang Xu, Yingcong Chen
The fidelity of Generative Adversarial Networks (GAN) inversion is impeded by Out-Of-Domain (OOD) areas (e.g., background, accessories) in the image. Detecting the OOD areas beyond…
S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention
Chiyu Zhang, Xiaogang Xu, Lei Wang +2
Transformer's recent integration into style transfer leverages its proficiency in establishing long-range dependencies, albeit at the expense of attenuated local modeling. This pap…
Local Low-light Image Enhancement via Region-Aware Normalization
Shihurong Yao, Yizhan Huang, Xiaogang Xu
In the realm of Low-Light Image Enhancement (LLIE), existing research primarily focuses on enhancing images globally. However, many applications require local LLIE, where users are…
DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation
Xin Lai, Zhuotao Tian, Xiaogang Xu +5
Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations. It leverages a labeled source domain dataset…
Universal Adaptive Data Augmentation
Xiaogang Xu, Hengshuang Zhao
Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are n…
Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution
Xiaogang Xu, Ruixing Wang, Chi-Wing Fu +1
Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy. The curren…
Towards Real-World Video Denosing: A Practical Video Denosing Dataset and Network
Xiaogang Xu, Yitong Yu, Nianjuan Jiang +3
To facilitate video denoising research, we construct a compelling dataset, namely, "Practical Video Denoising Dataset" (PVDD), containing 200 noisy-clean dynamic video pairs in bot…