Yixiao Li

Yixiao Li

Auto-generated profile, based on publicly available information

Yixiao Li

School of Mathematical Sciences, Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 November 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YLYixiao Li
Yixiao Li
XYXiaoyuan Yang
Xiaoyuan Yang
GYGuanghui Yue
Guanghui Yue
JFJun Fu
Jun Fu
Qiuping JiangQiuping Jiang
Qiuping Jiang
WZWei Zhou
Wei Zhou
Many super-resolution (SR) algorithms have been proposed to increase image resolution. However, full-reference (FR) image quality assessment (IQA) metrics for comparing and evaluating different SR algorithms are limited. In this work, we propose the Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA, which is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module. First, we encode the input images for feature representations. Inspired by the characteristics of the human visual system, we then construct the perception-oriented PBA module. Specifically, different from existing attention-based SR IQA methods, we conceive a Bidirectional Attention to bidirectionally construct visual attention to distortion, which is consistent with the generation and evaluation processes of SR images. To further guide the quality assessment towards the perception of distorted information, we propose Grouped Multi-scale Deformable Convolution, enabling the proposed method to adaptively perceive distortion. Moreover, we design Sub-information Excitation Convolution to direct visual perception to both sub-pixel and sub-channel attention. Finally, the quality prediction module is exploited to integrate quality-aware features and regress quality scores. Extensive experiments demonstrate that our proposed PBAN outperforms state-of-the-art quality assessment methods.

8 July 2025 in Displays
Verified
Journal Article
Closed access
YLYixiao Li
Yixiao Li
XYXiaoyuan Yang
Xiaoyuan Yang
YLYuqing Luo
Yuqing Luo
HAHadi Amirpour
Hadi Amirpour
HLHantao Liu
Hantao Liu
WZWei Zhou
Wei Zhou

28 March 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HZHaoying Zeng
Haoying Zeng
XYXiaoyuan Yang
Xiaoyuan Yang
KSKangqing Shen
Kangqing Shen
YLYixiao Li
Yixiao Li
JJJin Jiang
Jin Jiang
FLFangyi Li
Fangyi Li
Deep learning-based pansharpening has been widely applied in high-resolution imaging. Yet, artifacts related to generalization and over-smoothing have continuously been the challenge, primarily due to the mismatch between the simulation dataset and the unseen real-world scenarios. Current approaches address these through unsupervised frameworks or generative models, while modal inconsistency are not fully considered, leading to suboptimal performance. In this paper, we propose a contrastive cross-modal framework via uncertainty guidance (UGCC), which comprises of three key modules: a contrast feature enhancement module (CFEM), a cross-modal compensation module (CMCM) and an uncertainty guidance module (UGM). Firstly, to enhance generalization and reduce over-fitting, CFEM is introduced. Robust contrast features are augmented and learned sparsely in latent space, where sample distributions are refined, and redundant information is filtered from highly similar sample pairs for enhanced training stability. Furthermore, CMCM mitigates modal inconsistency effectively by domain transfer and collaborative attention, achieving efficient modal separation and interaction. Finally, to adaptively balancing the performance of CMCM and CFEM based on prediction confidence, a hybrid loss function is designed, where UGM adjusts the weights through quantifying statistical-versus-structural uncertainties. Extensive experiments on Quickbird, Gaofen-2, WorldView-2, and WorldView-3 demonstrate that the performance of the proposed method surpasses or matches the state of arts. Furthermore, ablation studies validate the effectiveness of each component. The code is now available at: https://github.com/meimeizeng/UGCF.