Xin He

Mr. Xin He

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
19 June 2024 in Sensors
Verified
Journal Article
Open access
PDF file
YZYaoqing Zhang
Yaoqing Zhang
XHXin He
Xin He
CZChunxia Zhan
Chunxia Zhan
JLJunjie Li
Junjie Li
Remote sensing images are inevitably affected by the degradation of haze with complex appearance and non-uniform distribution, which remarkably affects the effectiveness of downstream remote sensing visual tasks. However, most current methods principally operate in the original pixel space of the image, which hinders the exploration of the frequency characteristics of remote sensing images, resulting in these models failing to fully exploit their representation ability to produce high-quality images. This paper proposes a frequency-oriented remote sensing dehazing Transformer named FOTformer, to explore information in the frequency domain to eliminate disturbances caused by haze in remote sensing images. It contains three components. Specifically, we developed a frequency-prompt attention evaluator to estimate the self-correlation of features in the frequency domain rather than the spatial domain, improving the image restoration performance. We propose a content reconstruction feed-forward network that captures information between different scales in features and integrates and processes global frequency domain information and local multi-scale spatial information in Fourier space to reconstruct the global content under the guidance of the amplitude spectrum. We designed a spatial-frequency aggregation block to exchange and fuse features from the frequency domain and spatial domain of the encoder and decoder to facilitate the propagation of features from the encoder stream to the decoder and alleviate the problem of information loss in the network. The experimental results show that the FOTformer achieved a more competitive performance against other remote sensing dehazing methods on commonly used benchmark datasets.

5 July 2023 in Digital Signal Processing
Verified
Journal Article
Closed access
DYDawei Yang
Dawei Yang
XHXin He
Xin He
RZRuiheng Zhang
Ruiheng Zhang

29 January 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SWShuang Wu
Shuang Wu
XHXin He
Xin He
XCXiang Chen
Xiang Chen
Adverse weather conditions, such as haze and raindrop, consistently degrade the quality of remote sensing images and affect subsequent vision-based applications. Recent years have witnessed advancements in convolutional neural networks (CNNs) and Transformers in the field of remote sensing image restoration. However, these methods either suffer from limited receptive fields or incur quadratic computational overhead, leading to an imbalance between performance and model efficiency. In this paper, we propose an effective vision state space model (called Weamba) for remote sensing image restoration by modeling long-range pixel dependencies with linear complexity. Specifically, we develop a local-enhanced state space module to better aggregate rich local and global information, both of which are complementary and beneficial for high-quality image reconstruction. Furthermore, we design a multi-router scanning strategy for spatially varying feature extraction, alleviating the issue of redundant information caused by repeated scanning directions in existing methods. Extensive experiments on multiple benchmarks show that the proposed Weamba performs favorably against state-of-the-art approaches.

24 June 2022 in IEEE Access
Verified
Journal Article
Open access
XHXin He
Xin He
WJWanfeng Ji
Wanfeng Ji
JXJinpeng Xie
Jinpeng Xie
Aerial image dehazing is an important preprocessing step, since haze extremely degrades the imaging quality and affects subsequent the applications of aerial imagery. Most current haze removal methods achieve encouraging performance by relying on paired synthetic data, while are limited to their generality and scalability in the practical tasks. To this end, this paper aims to learn an effective unsupervised dehazing model from an unpaired set of clear and hazy aerial images. Motivated by the great advantages of contrastive learning in unsupervised representation field, we first attempt to formulate a Asymmetric Contrastive CycleGAN dehazing framework (namely ACC-GAN) to maximize the mutual information between the hazy domain and the haze-free domain. In the latent representation space, the introduced contrastive constraint ensures that the restored image is pulled closer to the clear image and pushed away from the hazy image, so as to indirectly regularize the unsupervised dehazing process. Importantly, different from the standard CycleGAN, we develop an additional feature transfer network into the forward path to form the asymmetric structure of ACC-GAN, which can enhance encoded features from hazy domain to haze-free domain. During training, multi-dimension loss terms are jointly built into a loss committee for generating dehazed results with higher naturalness and better fidelity. Experimental results on synthesis and real-world datasets indicate that our method is superior to existing unsupervised dehazing approaches, and is also very competitive to other related supervised models.

25 April 2024 in Frontiers in Marine Science
Verified
Journal Article
Open access
XHXin He
Xin He
JLJunjie Li
Junjie Li
TJTong Jia
Tong Jia
Underwater image super-resolution is vital for enhancing the clarity and detail of underwater imagery, enabling improved analysis, navigation, and exploration in underwater environments where visual quality is typically degraded due to factors like water turbidity and light attenuation. In this paper, we propose an effective hybrid dynamic Transformer (called HDT-Net) for underwater image super-resolution, leveraging a collaborative exploration of both local and global information aggregation to help image restoration. Firstly, we introduce a dynamic local self-attention to adaptively capture important spatial details in degraded underwater images by employing dynamic weighting. Secondly, considering that visual transformers tend to introduce irrelevant information when modeling the global context, thereby interfering with the reconstruction of high-resolution images, we design a sparse non-local self-attention to more accurately compute self-similarity by setting a top-k threshold. Finally, we integrate these two self-attention mechanisms into the hybrid dynamic transformer module, constituting the primary feature extraction unit of our proposed method. Quantitative and qualitative analyses on benchmark datasets demonstrate that our approach achieves superior performance compared to previous CNN and Transformer models.

9 July 2024 in Symmetry
Verified
Journal Article
Open access
PDF file
YZYaoqing Zhang
Yaoqing Zhang
XHXin He
Xin He
CZChunxia Zhan
Chunxia Zhan
JLJunjie Li
Junjie Li
Image deraining aims to mitigate the adverse effects of rain streaks on image quality. Recently, the advent of convolutional neural networks (CNNs) and Vision Transformers (ViTs) has catalyzed substantial advancements in this field. However, these methods fail to effectively balance model efficiency and image deraining performance. In this paper, we propose an effective, locally enhanced visual state space model for image deraining, called DerainMamba. Specifically, we introduce a global-aware state space model to better capture long-range dependencies with linear complexity. In contrast to existing methods that utilize fixed unidirectional scan mechanisms, we propose a direction-aware symmetrical scanning module to enhance the feature capture of rain streak direction. Furthermore, we integrate a local-aware mixture of experts into our framework to mitigate local pixel forgetting, thereby enhancing the overall quality of high-resolution image reconstruction. Experimental results validate that the proposed method surpasses state-of-the-art approaches on six benchmark datasets.