Shouyi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shouyi Wang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Chao Ren
Sichuan University
2 shared publications - Di Wu
Department of Electrical and Computer Engineering, North Dakota State University, Fargo, ND, USA
1 shared publication Gang Liu
1 shared publication- Haosong Gou
IT Department, China Mobile Group Sichuan Company Ltd., Chengdu, China
1 shared publication - Jun Wu
Huazhong University of Science and Technology
1 shared publication Lu Haiqing
State Grid Zhejiang Pinghu City Power Supply Co., Ltd., Zhejiang Pinghu, China
1 shared publication
Latest Publications
- 24 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 18448-18462
GBPG-Net: Global Background Prior-Guided Rain and Snow Image Restoration
The aim of image restoration in the presence of rain and snow effects is to eliminate these disturbances while retaining the underlying background structure. Most existing methods tend to directly learn the mapping from corrupted images to clean ones, often resulting in residual rain or snow artifacts and compromised background structures. In this work, both theoretical analysis and experimental findings confirm the robustness of the hue channel in HSV color space to rain and snow disturbances, even when extracted from corrupted images. Motivated by this insight, we propose to leverage the global clean background cues inherent in the hue channel to guide the network in preserving the image background structure and removing interference. To this end, we introduce the global background prior-guided network (GBPG-Net) for restoring rain and snow-affected images, which employs a triangular formation to facilitate continuous interaction and updating of the global background prior (GBP) with the image feature within the GBPG-unit, resulting in improved interference removal and background structure preservation. Specifically, the GBPG-Net incorporates the global clean background prior injector (GCBPI) to inject the GBP into the network. Subsequently, the prior-guided local detail excavation (PGLDE) module, built on GCBPI, further refines interference removal and structure preservation to process local details intricately. Finally, the prior-guided local-global aggregation (PGLGA) module aggregates global background features with local detailed features, enabling the network to better understand the overall content and subtle interference for more accurate reconstruction. Quantitative and qualitative evaluations on synthetic and real datasets demonstrate the effectiveness of the proposed GBPG-Net in deraining and desnowing tasks, highlighting its advantages over existing methods. The code and supplementary documentation are available at https://github.com/liux520/GBPG-Net
- 24 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (10) , 18448-18462
GBPG-Net: Global Background Prior-Guided Rain and Snow Image Restoration
The aim of image restoration in the presence of rain and snow effects is to eliminate these disturbances while retaining the underlying background structure. Most existing methods tend to directly learn the mapping from corrupted images to clean ones, often resulting in residual rain or snow artifacts and compromised background structures. In this work, both theoretical analysis and experimental findings confirm the robustness of the hue channel in HSV color space to rain and snow disturbances, even when extracted from corrupted images. Motivated by this insight, we propose to leverage the global clean background cues inherent in the hue channel to guide the network in preserving the image background structure and removing interference. To this end, we introduce the global background prior-guided network (GBPG-Net) for restoring rain and snow-affected images, which employs a triangular formation to facilitate continuous interaction and updating of the global background prior (GBP) with the image feature within the GBPG-unit, resulting in improved interference removal and background structure preservation. Specifically, the GBPG-Net incorporates the global clean background prior injector (GCBPI) to inject the GBP into the network. Subsequently, the prior-guided local detail excavation (PGLDE) module, built on GCBPI, further refines interference removal and structure preservation to process local details intricately. Finally, the prior-guided local-global aggregation (PGLGA) module aggregates global background features with local detailed features, enabling the network to better understand the overall content and subtle interference for more accurate reconstruction. Quantitative and qualitative evaluations on synthetic and real datasets demonstrate the effectiveness of the proposed GBPG-Net in deraining and desnowing tasks, highlighting its advantages over existing methods. The code and supplementary documentation are available at https://github.com/liux520/GBPG-Net
- 21 December 2024
- Published by Elsevier in Neurocomputing
- Vol. 620
Efficient image super resolution via Mixed Window and Dimension Interaction
- 21 December 2024
- Published by Elsevier in Neurocomputing
- Vol. 620
Efficient image super resolution via Mixed Window and Dimension Interaction
- Open Access
- 14 October 2021
- Published by Frontiers Media SA in Frontiers in Energy Research
- Vol. 9
Research and Application of a Clear Diamond-Shaped Distribution Network Structure
Aiming at the problems of low power supply reliability, poor transfer capacity between stations, and low line utilization in the current distribution network, this paper proposes a diamond-shaped distribution network structure with a clear structure. First, we investigated the typical wiring patterns of medium-voltage distribution networks in Tokyo, Japan, Paris, France, and China’s developed cities, and summarized experience and shortcomings. Secondly, combining the typical wiring patterns of distribution networks in China and abroad, construct a diamond-shaped distribution network structure, and study its adaptability, safety and flexibility, power supply reliability, and economy. Finally, take the transformation of the wiring mode of a regional distribution network in a certain city as an example, compare the use of the diamond-shaped distribution network structure in this article with the use of cable double-ring network wiring, cable “double petal” wiring, and Shanghai diamond-type wiring distribution network grid reconstruction The effect verifies the superiority of the diamond-shaped distribution network structure in this paper.
- 14 October 2021
- Published by Frontiers Media SA in Frontiers in Energy Research
- Vol. 9
Open AccessResearch and Application of a Clear Diamond-Shaped Distribution Network Structure
Aiming at the problems of low power supply reliability, poor transfer capacity between stations, and low line utilization in the current distribution network, this paper proposes a diamond-shaped distribution network structure with a clear structure. First, we investigated the typical wiring patterns of medium-voltage distribution networks in Tokyo, Japan, Paris, France, and China’s developed cities, and summarized experience and shortcomings. Secondly, combining the typical wiring patterns of distribution networks in China and abroad, construct a diamond-shaped distribution network structure, and study its adaptability, safety and flexibility, power supply reliability, and economy. Finally, take the transformation of the wiring mode of a regional distribution network in a certain city as an example, compare the use of the diamond-shaped distribution network structure in this article with the use of cable double-ring network wiring, cable “double petal” wiring, and Shanghai diamond-type wiring distribution network grid reconstruction The effect verifies the superiority of the diamond-shaped distribution network structure in this paper.
- 1 March 2008
- Published by World Scientific Pub Co Pte Ltd in Asian-European Journal of Mathematics
- Vol. 01 (01) , 77-83
THERE DOES NOT EXIST AN ODD SINGULAR NUMBER OF THE FORM plqr
Motivated by his solution to the Bourque-Ligh conjecture on the nonsingularity of the least common multiple matrix defined on the gcd-closed set, Hong introduced the concept of primitive singular number. Meanwhile Hong proved that there does not exist a singular number with no more than two distinct prime factors. Hong and Shum as well Sun showed in 2006 that there are even primitive singular numbers of the form plqr, where p, q, r are distinct primes and l is a positive integer. In this paper, we show that there does not exist an odd singular number of the form plqr. This improves a result obtained by Hong and Shum as well Sun and also confirms partially a conjecture of Hong.
- 1 March 2008
- Published by World Scientific Pub Co Pte Ltd in Asian-European Journal of Mathematics
- Vol. 01 (01) , 77-83
THERE DOES NOT EXIST AN ODD SINGULAR NUMBER OF THE FORM plqr
Motivated by his solution to the Bourque-Ligh conjecture on the nonsingularity of the least common multiple matrix defined on the gcd-closed set, Hong introduced the concept of primitive singular number. Meanwhile Hong proved that there does not exist a singular number with no more than two distinct prime factors. Hong and Shum as well Sun showed in 2006 that there are even primitive singular numbers of the form plqr, where p, q, r are distinct primes and l is a positive integer. In this paper, we show that there does not exist an odd singular number of the form plqr. This improves a result obtained by Hong and Shum as well Sun and also confirms partially a conjecture of Hong.