Query：
学者姓名：赵铁松
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Hairstyle transfer is challenging due to intricate nature of hairstyles. In particular, face misalignment leads to distortion or deformation of the transferred hairstyle. To address this issue, we propose a Robust and Efficient Hairstyle transfer (REHair) framework, which comprises three stages: adaptive angle alignment, adaptive depth alignment, and efficient hairstyle editing. Firstly, we perform head pose estimation and adjust the facial rotation angle based on the latent code, thus ensuring consistent facial orientation between the face image and the hairstyle reference image and preventing hair shape and texture loss from iterative optimization methods. Secondly, we employ monocular depth estimation to predict the face depth of both images and perform adaptive depth alignment, ensuring the preservation of more hairstyle details. Finally, we propose a fast image embedding algorithm and integrate it with the latent code, significantly reducing the image embedding time in StyleGAN2. This adaptation enables REHair to be suitable for real-time applications. Quantitative and qualitative evaluations on the FFHQ and CelebA-HQ dataset demonstrate that REHair achieves state-of-the-art performance by successfully transferring hairstyles between images with different poses. The proposed method significantly reduces image embedding time while preserving image quality, and effectively addresses challenges associated with sub-optimal photography conditions and slow generation speed. Source code avaliable at https://github.com/fdwxfy/REHair.
Keyword ：
Adaptive angle alignment Adaptive angle alignment Adaptive depth alignment Adaptive depth alignment Face misalignment Face misalignment Fast image embedding Fast image embedding Hairstyle transfer Hairstyle transfer
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Yiwen , Ling, Liping , Lin, Qingxu et al. REHair: Efficient hairstyle transfer robust to face misalignment [J]. | PATTERN RECOGNITION , 2025 , 164 . |
| MLA | Xu, Yiwen et al. "REHair: Efficient hairstyle transfer robust to face misalignment" . | PATTERN RECOGNITION 164 (2025) . |
| APA | Xu, Yiwen , Ling, Liping , Lin, Qingxu , Fang, Ying , Zhao, Tiesong . REHair: Efficient hairstyle transfer robust to face misalignment . | PATTERN RECOGNITION , 2025 , 164 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Due to the complex underwater imaging environment, existing Underwater Image Enhancement (UIE) techniques are unable to handle the increasing demand for high-quality underwater content in broadcasting systems. Thus, a robust quality assessment method is highly expected to effectively compare the quality of different enhanced underwater images. To this end, we propose a novel quality assessment method for enhanced underwater images by utilizing multiple levels of features at various stages of the network's depth. We first select underwater images with different distortions to analyze the characteristics of different UIE results at various feature levels. We found that low-level features are more sensitive to color information, while mid-level features are more indicative of structural differences. Based on this, a Channel-Spatial-Pixel Attention Module (CSPAM) is designed for low-level perception to capture color characteristics, utilizing channel, spatial, and pixel dimensions. To capture structural variations, a Parallel Structural Perception Module (PSPM) with convolutional kernels of different scales is introduced for mid-level perception. For high-level perception, due to the accumulation of noise, an Adaptive Weighted Downsampling (AWD) layer is employed to restore the semantic information. Furthermore, a new top-down multi-level feature fusion method is designed. Information from different levels is integrated through a Selective Feature Fusion (SFF) mechanism, which produces semantically rich features and enhances the model's feature representation capability. Experimental results demonstrate the superior performance of the proposed method over the competing image quality evaluation methods.
Keyword ：
image quality assessment image quality assessment multi-level perception multi-level perception Underwater image enhancement Underwater image enhancement
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Yiwen , Lin, Yuxiang , He, Nian et al. Multi-Level Perception Assessment for Underwater Image Enhancement [J]. | IEEE TRANSACTIONS ON BROADCASTING , 2025 , 71 (2) : 606-615 . |
| MLA | Xu, Yiwen et al. "Multi-Level Perception Assessment for Underwater Image Enhancement" . | IEEE TRANSACTIONS ON BROADCASTING 71 . 2 (2025) : 606-615 . |
| APA | Xu, Yiwen , Lin, Yuxiang , He, Nian , Wang, Xuejin , Zhao, Tiesong . Multi-Level Perception Assessment for Underwater Image Enhancement . | IEEE TRANSACTIONS ON BROADCASTING , 2025 , 71 (2) , 606-615 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Video compression artifact removal focuses on enhancing the visual quality of compressed videos by mitigating visual distortions. However, existing methods often struggle to effectively capture spatio-temporal features and recover high-frequency details, due to their suboptimal adaptation to the characteristics of compression artifacts. To overcome these limitations, we propose a novel Spatio-Temporal and Frequency Fusion (STFF) framework. STFF incorporates three key components: Feature Extraction and Alignment (FEA), which employs SRU for effective spatiotemporal feature extraction; Bidirectional High-Frequency Enhanced Propagation (BHFEP), which integrates HCAB to restore high-frequency details through bidirectional propagation; and Residual High-Frequency Refinement (RHFR), which further enhances high-frequency information. Extensive experiments demonstrate that STFF achieves superior performance compared to state-of-the-art methods in both objective metrics and subjective visual quality, effectively addressing the challenges posed by video compression artifacts. Trained model available: https://github.com/Stars-WMX/STFF.
Keyword ：
Degradation Degradation Feature extraction Feature extraction Image coding Image coding Image restoration Image restoration Motion compensation Motion compensation Optical flow Optical flow Quality assessment Quality assessment Spatiotemporal phenomena Spatiotemporal phenomena Transformers Transformers video coding video coding Video compression Video compression Video compression artifact removal Video compression artifact removal video enhancement video enhancement video quality video quality
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Mingxing , Liao, Yipeng , Chen, Weiling et al. STFF: Spatio-Temporal and Frequency Fusion for Video Compression Artifact Removal [J]. | IEEE TRANSACTIONS ON BROADCASTING , 2025 , 71 (2) : 542-554 . |
| MLA | Wang, Mingxing et al. "STFF: Spatio-Temporal and Frequency Fusion for Video Compression Artifact Removal" . | IEEE TRANSACTIONS ON BROADCASTING 71 . 2 (2025) : 542-554 . |
| APA | Wang, Mingxing , Liao, Yipeng , Chen, Weiling , Lin, Liqun , Zhao, Tiesong . STFF: Spatio-Temporal and Frequency Fusion for Video Compression Artifact Removal . | IEEE TRANSACTIONS ON BROADCASTING , 2025 , 71 (2) , 542-554 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Anomaly detection can significantly aid doctors in interpreting chest X-rays. The commonly used strategy involves utilizing the pre-trained network to extract features from normal data to establish feature representations. However, when a pre-trained network is applied to more detailed X-rays, differences of similarity can limit the robustness of these feature representations. Therefore, we propose an intra- and inter-correlation learning framework for chest X-ray anomaly detection. Firstly, to better leverage the similar anatomical structure information in chest X-rays, we introduce the Anatomical-Feature Pyramid Fusion Module for feature fusion. This module aims to obtain fusion features with both local details and global contextual information. These fusion features are initialized by a trainable feature mapper and stored in a feature bank to serve as centers for learning. Furthermore, to Facing Differences of Similarity (FDS) introduced by the pre-trained network, we propose an intra- and inter-correlation learning strategy: 1) We use intra-correlation learning to establish intra-correlation between mapped features of individual images and semantic centers, thereby initially discovering lesions; 2) We employ inter-correlation learning to establish inter-correlation between mapped features of different images, further mitigating the differences of similarity introduced by the pre-trained network, and achieving effective detection results even in diverse chest disease environments. Finally, a comparison with 18 state-of-the-art methods on three datasets demonstrates the superiority and effectiveness of the proposed method across various scenarios.
Keyword ：
chest X-ray chest X-ray correlation learning correlation learning feature fusion feature fusion Medical anomaly detection Medical anomaly detection transfer learning transfer learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Shicheng , Li, Wei , Li, Zuoyong et al. Facing Differences of Similarity: Intra- and Inter-Correlation Unsupervised Learning for Chest X-Ray Anomaly Detection [J]. | IEEE TRANSACTIONS ON MEDICAL IMAGING , 2025 , 44 (2) : 801-814 . |
| MLA | Xu, Shicheng et al. "Facing Differences of Similarity: Intra- and Inter-Correlation Unsupervised Learning for Chest X-Ray Anomaly Detection" . | IEEE TRANSACTIONS ON MEDICAL IMAGING 44 . 2 (2025) : 801-814 . |
| APA | Xu, Shicheng , Li, Wei , Li, Zuoyong , Zhao, Tiesong , Zhang, Bob . Facing Differences of Similarity: Intra- and Inter-Correlation Unsupervised Learning for Chest X-Ray Anomaly Detection . | IEEE TRANSACTIONS ON MEDICAL IMAGING , 2025 , 44 (2) , 801-814 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Sonar technology has been widely used in underwater surface mapping and remote object detection for its light-independent characteristics. Recently, the booming of artificial intelligence further surges sonar image (SI) processing and understanding techniques. However, the intricate marine environments and diverse nonlinear postprocessing operations may degrade the quality of SIs, impeding accurate interpretation of underwater information. Efficient image quality assessment (IQA) methods are crucial for quality monitoring in sonar imaging and processing. Existing IQA methods overlook the unique characteristics of SIs or focus solely on typical distortions in specific scenarios, which limits their generalization capability. In this article, we propose a unified sonar IQA method, which overcomes the challenges posed by diverse distortions. Though degradation conditions are changeable, ideal SIs consistently require certain properties that must be task-centered and exhibit attribute consistency. We derive a comprehensive set of quality attributes from both the task background and visual content of SIs. These attribute features are represented in just ten dimensions and ultimately mapped to the quality score. To validate the effectiveness of our method, we construct the first comprehensive SI dataset. Experimental results demonstrate the superior performance and robustness of the proposed method.
Keyword ：
Attribute consistency Attribute consistency Degradation Degradation Distortion Distortion Image quality Image quality image quality assessment (IQA) image quality assessment (IQA) Imaging Imaging Noise Noise Nonlinear distortion Nonlinear distortion no-reference (NR) no-reference (NR) Quality assessment Quality assessment Silicon Silicon Sonar Sonar sonar imaging and processing sonar imaging and processing Sonar measurements Sonar measurements
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cai, Boqin , Chen, Weiling , Zhang, Jianghe et al. Unified No-Reference Quality Assessment for Sonar Imaging and Processing [J]. | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2025 , 63 . |
| MLA | Cai, Boqin et al. "Unified No-Reference Quality Assessment for Sonar Imaging and Processing" . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63 (2025) . |
| APA | Cai, Boqin , Chen, Weiling , Zhang, Jianghe , Junejo, Naveed Ur Rehman , Zhao, Tiesong . Unified No-Reference Quality Assessment for Sonar Imaging and Processing . | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING , 2025 , 63 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The introduction of multiple viewpoints in video scenes inevitably increases the bitrates required for storage and transmission. To reduce bitrates, researchers have developed methods to skip intermediate viewpoints during compression and delivery, and ultimately reconstruct them using Side Information (SInfo). Typically, depth maps are used to construct SInfo. However, these methods suffer from reconstruction inaccuracies and inherently high bitrates. In this paper, we propose a novel multi-view video coding method that leverages the image generation capabilities of Generative Adversarial Network (GAN) to improve the reconstruction accuracy of SInfo. Additionally, we consider incorporating information from adjacent temporal and spatial viewpoints to further reduce SInfo redundancy. At the encoder, we construct a spatio-temporal Epipolar Plane Image (EPI) and further utilize a convolutional network to extract the latent code of a GAN as SInfo. At the decoder, we combine the SInfo and adjacent viewpoints to reconstruct intermediate views using the GAN generator. Specifically, we establish a joint encoder constraint for reconstruction cost and SInfo entropy to achieve an optimal trade-off between reconstruction quality and bitrate overhead. Experiments demonstrate the significant improvement in Rate-Distortion (RD) performance compared to state-of-the-art methods.
Keyword ：
Epipolar plane image Epipolar plane image Generative adversarial network Generative adversarial network Latent code learning Latent code learning Multi-view video coding Multi-view video coding
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lan, Chengdong , Yan, Hao , Luo, Cheng et al. GAN-based multi-view video coding with spatio-temporal EPI reconstruction [J]. | SIGNAL PROCESSING-IMAGE COMMUNICATION , 2025 , 132 . |
| MLA | Lan, Chengdong et al. "GAN-based multi-view video coding with spatio-temporal EPI reconstruction" . | SIGNAL PROCESSING-IMAGE COMMUNICATION 132 (2025) . |
| APA | Lan, Chengdong , Yan, Hao , Luo, Cheng , Zhao, Tiesong . GAN-based multi-view video coding with spatio-temporal EPI reconstruction . | SIGNAL PROCESSING-IMAGE COMMUNICATION , 2025 , 132 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Capturing images at night are susceptible to inadequate illumination conditions and motion blurring. Given the typical coupling of these two forms of degradation, a pioneer work takes a compact approach of brightening followed by deblurring. However, this sequential approach may compromise informative features and elevate the likelihood of generating unintended artifacts. In this paper, we observe that the co-existing low light and blurs intuitively impair multiple perceptions, making it difficult to produce visually appealing results. To meet these challenges, we propose perceptual decoupling with heterogeneous auxiliary tasks (PDHAT) for joint low-light image enhancement and deblurring. Based on the crucial perceptual properties of the two degradations, we construct two individual auxiliary tasks: coarse preview prediction (CPP) and high-frequency reconstruction (HFR), so that the perception of color, brightness, edges, and details are decoupled into heterogeneous auxiliary tasks to obtain task-specific representations for parallel assisting the main task: joint low-light enhancement and deblurring (LLE-Deblur). Furthermore, we develop dedicated modules to build the network blocks in each branch based on the exclusive properties of each task. Comprehensive experiments are conducted on LOL-Blur and Real-LOL-Blur datasets, showing that our method outperforms existing methods on quantitative metrics and qualitative results.
Keyword ：
Brightness Brightness Degradation Degradation Feature extraction Feature extraction image deblurring image deblurring Image enhancement Image enhancement Image reconstruction Image reconstruction Image restoration Image restoration joint solution joint solution low-light image enhancement low-light image enhancement Multiple degradations Multiple degradations Task analysis Task analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Yuezhou , Xu, Rui , Niu, Yuzhen et al. Perceptual Decoupling With Heterogeneous Auxiliary Tasks for Joint Low-Light Image Enhancement and Deblurring [J]. | IEEE TRANSACTIONS ON MULTIMEDIA , 2024 , 26 : 6663-6675 . |
| MLA | Li, Yuezhou et al. "Perceptual Decoupling With Heterogeneous Auxiliary Tasks for Joint Low-Light Image Enhancement and Deblurring" . | IEEE TRANSACTIONS ON MULTIMEDIA 26 (2024) : 6663-6675 . |
| APA | Li, Yuezhou , Xu, Rui , Niu, Yuzhen , Guo, Wenzhong , Zhao, Tiesong . Perceptual Decoupling With Heterogeneous Auxiliary Tasks for Joint Low-Light Image Enhancement and Deblurring . | IEEE TRANSACTIONS ON MULTIMEDIA , 2024 , 26 , 6663-6675 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Natural video capturing suffers from visual blurriness due to high-motion of cameras or objects. Until now, the video blurriness removal task has been extensively explored for both human vision and machine processing. However, its computational cost is still a critical issue and has not yet been fully addressed. In this paper, we propose a novel Lightweight Video Deblurring (LightViD) method that achieves the top-tier performance with an extremely low parameter size. The proposed LightViD consists of a blur detector and a deblurring network. In particular, the blur detector effectively separate blurriness regions, thus avoid both unnecessary computation and over-enhancement on non-blurriness regions. The deblurring network is designed as a lightweight model. It employs a Spatial Feature Fusion Block (SFFB) to extract hierarchical spatial features, which are further fused by ConvLSTM for effective spatial-temporal feature representation. Comprehensive experiments with quantitative and qualitative comparisons demonstrate the effectiveness of our LightViD method, which achieves competitive performances on GoPro and DVD datasets, with reduced computational costs of 1.63M parameters and 96.8 GMACs. Trained model available: https://github.com/wgp/LightVid.
Keyword ：
blur detection blur detection Computational efficiency Computational efficiency Computational modeling Computational modeling Detectors Detectors Feature extraction Feature extraction Image restoration Image restoration Kernel Kernel spatial-temporal feature fusion spatial-temporal feature fusion Task analysis Task analysis Video deblurring Video deblurring
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Liqun , Wei, Guangpeng , Liu, Kanglin et al. LightViD: Efficient Video Deblurring With Spatial-Temporal Feature Fusion [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (8) : 7430-7439 . |
| MLA | Lin, Liqun et al. "LightViD: Efficient Video Deblurring With Spatial-Temporal Feature Fusion" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34 . 8 (2024) : 7430-7439 . |
| APA | Lin, Liqun , Wei, Guangpeng , Liu, Kanglin , Feng, Wanjian , Zhao, Tiesong . LightViD: Efficient Video Deblurring With Spatial-Temporal Feature Fusion . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (8) , 7430-7439 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Photos captured under low-light conditions suffer from multiple coupling problems, i.e., low brightness, color distortion, heavy noise, and detail degradation, making low-light image enhancement a challenging task. Existing deep learning-based low-light image enhancement methods typically focus on improving the illumination and color while neglecting the noise in the enhanced image. To solve the above problems, this paper proposes a low-light image enhancement method based on task decoupling. According to the different requirements for high-level and low-level features, the low-light image enhancement task is decoupled into two subtasks: illumination and color enhancement and detail reconstruction. Based on the task decoupling, we propose a two-branch low-light image enhancement network (TBLIEN). The illumination and color enhancement branch is built as a U-Net structure with global feature extraction, which exploits deep semantic information for illumination and color improvement. The detail reconstruction branch uses a fully convolutional network that preserves the original resolution while performing detail restoration and noise removal. In addition, for the detail reconstruction branch, we design a half-dual attention residual module. Our module enhances features through spatial and channel attention mechanisms while preserving their context, allowing precise detail reconstruction. Extensive experiments on real and synthetic datasets show that our model outperforms other state-of-the-art methods, and has better generalization capability. Our method is also applicable to other image enhancement tasks, i.e., underwater image enhancement. © 2024 Chinese Institute of Electronics. All rights reserved.
Keyword ：
Color Color Deep learning Deep learning Image enhancement Image enhancement Semantics Semantics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Niu, Yu-Zhen , Chen, Ming-Ming , Li, Yue-Zhou et al. Task Decoupling Guided Low-Light Image Enhancement [J]. | Acta Electronica Sinica , 2024 , 52 (1) : 34-45 . |
| MLA | Niu, Yu-Zhen et al. "Task Decoupling Guided Low-Light Image Enhancement" . | Acta Electronica Sinica 52 . 1 (2024) : 34-45 . |
| APA | Niu, Yu-Zhen , Chen, Ming-Ming , Li, Yue-Zhou , Zhao, Tie-Song . Task Decoupling Guided Low-Light Image Enhancement . | Acta Electronica Sinica , 2024 , 52 (1) , 34-45 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
低照度条件下拍摄的照片往往存在亮度低、颜色失真、噪声高、细节退化等多重耦合问题，因此低照度图像增强是一个具有挑战性的任务. 现有基于深度学习的低照度图像增强方法通常聚焦于对亮度和色彩的提升，导致增强图像中仍然存在噪声等缺陷. 针对上述问题，本文提出了一种基于任务解耦的低照度图像增强方法，根据低照度图像增强任务对高层和低层特征的不同需求，将该任务解耦为亮度与色彩增强和细节重构两组任务，进而构建双分支低照度图像增强网络模型（Two-Branch Low-light Image Enhancement Network，TBLIEN）. 其中，亮度与色彩增强分支采用带全局特征的U-Net结构，提取深层语义信息改善亮度与色彩；细节重构分支采用保持原始分辨率的全卷积网络实现细节复原和噪声去除. 此外，在细节重构分支中，本文提出一种半双重注意力残差模块，能在保留上下文特征的同时通过空间和通道注意力强化特征，从而实现更精细的细节重构. 在合成和真实数据集上的广泛实验表明，本文模型的性能超越了当前先进的低照度图像增强方法，并具有更好的泛化能力，且可适用于水下图像增强等其他图像增强任务.
Keyword ：
任务解耦 任务解耦 低照度图像增强 低照度图像增强 双分支网络模型 双分支网络模型 对比学习 对比学习 残差网络 残差网络
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 牛玉贞 , 陈铭铭 , 李悦洲 et al. 基于任务解耦的低照度图像增强方法 [J]. | 电子学报 , 2024 . |
| MLA | 牛玉贞 et al. "基于任务解耦的低照度图像增强方法" . | 电子学报 (2024) . |
| APA | 牛玉贞 , 陈铭铭 , 李悦洲 , 赵铁松 . 基于任务解耦的低照度图像增强方法 . | 电子学报 , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
