Chenglong Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chenglong Wang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Tao Yan
Jiangnan University
2 shared publications - Weilong Huang
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China
2 shared publications - Cihang Wei
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China
1 shared publication - Ke Xu
University of Science and Technology of China, Hefei, China
1 shared publication - Rynson W. H. Lau
City University of Hong Kong (Dongguan), Dongguan, China
1 shared publication - Weijiang He
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China
1 shared publication
Latest Publications
- Open Access
- 10 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (2) , 1-24
MDeRainNet: An Efficient Macro-pixel Image Rain Removal Network
Since raining weather always degrades image quality and poses significant challenges to most computer vision-based intelligent systems, image de-raining has been a hot research topic in computer vision community. Fortunately, in a rainy Light Field (LF) image, background obscured by rain streaks in one sub-view may be visible in the other sub-views, and implicit depth information and recorded 4D structural information may benefit rain streak detection and removal. However, existing LF image rain removal methods either do not fully exploit the global correlations of 4D LF data or only utilize partial sub-views (i.e., under-utilization of the rich angular information), resulting in sub-optimal rain removal performance and no-equally good quality for all de-rained sub-views. In this article, we propose an efficient neural network, called MDeRainNet , for rain streak removal from LF images. The proposed network adopts a multi-scale encoder–decoder architecture, which directly works on Macro-pixel Images (MPIs) for improving the rain removal performance. To fully model the global correlation between the spatial information and the angular information, we propose an Extended Spatial-angular Interaction (ESAI) module to merge the two types of information, in which a simple and effective Transformer-based Spatial-angular Interaction Attention (SAIA) block is also proposed for modeling long-range geometric correlations and making full use of the angular information. Furthermore, to improve the generalization performance of our network on real-world rainy scenes, we propose a novel semi-supervised learning framework for our MDeRainNet , which utilizes multi-level KL loss to bridge the domain gap between features of synthetic and that of real-world rain streaks and introduces colored-residue image-guided contrastive regularization to reconstruct rain-free images. Extensive experiments conducted on both synthetic and real-world Light Field Images (LFIs) demonstrate that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.
- 10 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (2) , 1-24
Open AccessMDeRainNet: An Efficient Macro-pixel Image Rain Removal Network
Since raining weather always degrades image quality and poses significant challenges to most computer vision-based intelligent systems, image de-raining has been a hot research topic in computer vision community. Fortunately, in a rainy Light Field (LF) image, background obscured by rain streaks in one sub-view may be visible in the other sub-views, and implicit depth information and recorded 4D structural information may benefit rain streak detection and removal. However, existing LF image rain removal methods either do not fully exploit the global correlations of 4D LF data or only utilize partial sub-views (i.e., under-utilization of the rich angular information), resulting in sub-optimal rain removal performance and no-equally good quality for all de-rained sub-views. In this article, we propose an efficient neural network, called MDeRainNet , for rain streak removal from LF images. The proposed network adopts a multi-scale encoder–decoder architecture, which directly works on Macro-pixel Images (MPIs) for improving the rain removal performance. To fully model the global correlation between the spatial information and the angular information, we propose an Extended Spatial-angular Interaction (ESAI) module to merge the two types of information, in which a simple and effective Transformer-based Spatial-angular Interaction Attention (SAIA) block is also proposed for modeling long-range geometric correlations and making full use of the angular information. Furthermore, to improve the generalization performance of our network on real-world rainy scenes, we propose a novel semi-supervised learning framework for our MDeRainNet , which utilizes multi-level KL loss to bridge the domain gap between features of synthetic and that of real-world rain streaks and introduces colored-residue image-guided contrastive regularization to reconstruct rain-free images. Extensive experiments conducted on both synthetic and real-world Light Field Images (LFIs) demonstrate that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.
- 8 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 11 (25730436) , 101-115
APANet: Asymmetrical Parallax Attention Network for Efficient Stereo Image Deraining
Recently, several stereo image deraining methods have been proposed to recover clean backgrounds from rainy stereo images by exploring and exploiting intra and inter-view information. Despite these methods have achieved great progress, they under-utilize the parallax information of input images, and do not take advantage of existing high-quality and abundant single image rainy datasets for learning. In this paper, we propose an effective and efficient network, named Asymmetrical Parallax Attention Network (APANet), for stereo image deraining. Specifically, to fully exploit the parallax information, we first adopt an External Attention Module (EAM), which consists of an external attention block with two learnable memories, and a gated feedforward network, for achieving a better feature representation by incorporating the correlations between all samples. Subsequently, we propose an Asymmetrical Parallax Attention Module (APAM) to efficiently exploit the cross-attention between the features separately extracted from the left and right views, which filters useless stereo feature relationships with a well-designed mask calculated by excavating the parallax information (positional information of each matched pixel pair within a stereo image). For learning our network, we also construct an unpaired real-world stereo rainy image dataset, called StereoRealRain, which consists of some video clips (including 11803 image pairs). Moreover, we also introduce a Single-to-Stereo Image Deraining Distillation strategy for transferring the knowledge learned from single images deraining to stereo images deraining to improve the generalization ability of our network. Extensive experiments conducted on synthetic and real-world stereo rainy datasets demonstrate the effectiveness of our method. Our code and dataset will be available at https://github.com/YT3DVision/APANet .
- 8 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 11 (25730436) , 101-115
APANet: Asymmetrical Parallax Attention Network for Efficient Stereo Image Deraining
Recently, several stereo image deraining methods have been proposed to recover clean backgrounds from rainy stereo images by exploring and exploiting intra and inter-view information. Despite these methods have achieved great progress, they under-utilize the parallax information of input images, and do not take advantage of existing high-quality and abundant single image rainy datasets for learning. In this paper, we propose an effective and efficient network, named Asymmetrical Parallax Attention Network (APANet), for stereo image deraining. Specifically, to fully exploit the parallax information, we first adopt an External Attention Module (EAM), which consists of an external attention block with two learnable memories, and a gated feedforward network, for achieving a better feature representation by incorporating the correlations between all samples. Subsequently, we propose an Asymmetrical Parallax Attention Module (APAM) to efficiently exploit the cross-attention between the features separately extracted from the left and right views, which filters useless stereo feature relationships with a well-designed mask calculated by excavating the parallax information (positional information of each matched pixel pair within a stereo image). For learning our network, we also construct an unpaired real-world stereo rainy image dataset, called StereoRealRain, which consists of some video clips (including 11803 image pairs). Moreover, we also introduce a Single-to-Stereo Image Deraining Distillation strategy for transferring the knowledge learned from single images deraining to stereo images deraining to improve the generalization ability of our network. Extensive experiments conducted on synthetic and real-world stereo rainy datasets demonstrate the effectiveness of our method. Our code and dataset will be available at https://github.com/YT3DVision/APANet .