Zhengxue Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhengxue Wang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Guangwei Gao
Nanjing University of Science and Technology, Nanjing, China
4 shared publications - Jian Yang
Nanjing University of Science and Technology, Nanjing, China
3 shared publications Jian Yang
PCA Lab, Nanjing University of Science and Technology, China
2 shared publications- Jinshan Pan
Nanjing University of Science and Technology, Nanjing, China
2 shared publications - Ming-Hsuan Yang
University of California, Merced, USA
2 shared publications - Ying Tai
Nanjing University
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12432-12440
URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12432-12440
Open AccessURNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation
- Open Access
- 18 May 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (6) , 275
Correction: Scene Prior Filtering for Depth Super-Resolution
- 18 May 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (6) , 275
Open AccessCorrection: Scene Prior Filtering for Depth Super-Resolution
- 29 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (5) , 251
Scene Prior Filtering for Depth Super-Resolution
- 29 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (5) , 251
Scene Prior Filtering for Depth Super-Resolution
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (6) , 5823-5831
SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-resolution
Depth super-resolution (DSR) aims to restore high-resolution (HR) depth from low-resolution (LR) one, where RGB image is often used to promote this task. Recent image guided DSR approaches mainly focus on spatial domain to rebuild depth structure. However, since the structure of LR depth is usually blurry, only considering spatial domain is not very sufficient to acquire satisfactory results. In this paper, we propose structure guided network (SGNet), a method that pays more attention to gradient and frequency domains, both of which have the inherent ability to capture high-frequency structure. Specifically, we first introduce the gradient calibration module (GCM), which employs the accurate gradient prior of RGB to sharpen the LR depth structure. Then we present the Frequency Awareness Module (FAM) that recursively conducts multiple spectrum differencing blocks (SDB), each of which propagates the precise high-frequency components of RGB into the LR depth. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our SGNet, reaching the state-of-the-art (see Fig. 1). Codes and pre-trained models are available at https://github.com/yanzq95/SGNet.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (6) , 5823-5831
Open AccessSGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-resolution
Depth super-resolution (DSR) aims to restore high-resolution (HR) depth from low-resolution (LR) one, where RGB image is often used to promote this task. Recent image guided DSR approaches mainly focus on spatial domain to rebuild depth structure. However, since the structure of LR depth is usually blurry, only considering spatial domain is not very sufficient to acquire satisfactory results. In this paper, we propose structure guided network (SGNet), a method that pays more attention to gradient and frequency domains, both of which have the inherent ability to capture high-frequency structure. Specifically, we first introduce the gradient calibration module (GCM), which employs the accurate gradient prior of RGB to sharpen the LR depth structure. Then we present the Frequency Awareness Module (FAM) that recursively conducts multiple spectrum differencing blocks (SDB), each of which propagates the precise high-frequency components of RGB into the LR depth. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our SGNet, reaching the state-of-the-art (see Fig. 1). Codes and pre-trained models are available at https://github.com/yanzq95/SGNet.
- Open Access
SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution
Depth super-resolution (DSR) aims to restore high-resolution (HR) depth from low-resolution (LR) one, where RGB image is often used to promote this task. Recent image guided DSR approaches mainly focus on spatial domain to rebuild depth structure. However, since the structure of LR depth is usually blurry, only considering spatial domain is not very sufficient to acquire satisfactory results. In this paper, we propose structure guided network (SGNet), a method that pays more attention to gradient and frequency domains, both of which have the inherent ability to capture high-frequency structure. Specifically, we first introduce the gradient calibration module (GCM), which employs the accurate gradient prior of RGB to sharpen the LR depth structure. Then we present the Frequency Awareness Module (FAM) that recursively conducts multiple spectrum differencing blocks (SDB), each of which propagates the precise high-frequency components of RGB into the LR depth. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our SGNet, reaching the state-of-the-art. Codes and pre-trained models are available at https://github.com/yanzq95/SGNet.
Open AccessSGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution
Depth super-resolution (DSR) aims to restore high-resolution (HR) depth from low-resolution (LR) one, where RGB image is often used to promote this task. Recent image guided DSR approaches mainly focus on spatial domain to rebuild depth structure. However, since the structure of LR depth is usually blurry, only considering spatial domain is not very sufficient to acquire satisfactory results. In this paper, we propose structure guided network (SGNet), a method that pays more attention to gradient and frequency domains, both of which have the inherent ability to capture high-frequency structure. Specifically, we first introduce the gradient calibration module (GCM), which employs the accurate gradient prior of RGB to sharpen the LR depth structure. Then we present the Frequency Awareness Module (FAM) that recursively conducts multiple spectrum differencing blocks (SDB), each of which propagates the precise high-frequency components of RGB into the LR depth. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our SGNet, reaching the state-of-the-art. Codes and pre-trained models are available at https://github.com/yanzq95/SGNet.
- Open Access
- 25 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (3) , 1-15
Lightweight Feature De-redundancy and Self-calibration Network for Efficient Image Super-resolution
In recent years, thanks to the inherent powerful feature representation and learning abilities of the convolutional neural network (CNN), deep CNN-steered single image super-resolution approaches have achieved remarkable performance improvements. However, these methods are often accompanied by large consumption of computing and memory resources, which is difficult to be adopted in real-world application scenes. To handle this issue, we design an efficient Feature De-redundancy and Self-calibration Super-resolution network (FDSCSR). In particular, a Feature De-redundancy and Self-calibration Block (FDSCB) is proposed to reduce the repetitive feature information extracted by the model and further enhance the efficiency of the model. Then, based on FDSCB, a Local Feature Fusion Module is presented to elaborately utilize and fuse the feature information extracted by each FDSCB. Abundant experiments on benchmarks have demonstrated that our FDSCSR achieves superior performance with relatively less computational consumption and storage resource than other state-of-the-art approaches. The code is available at https://github.com/IVIPLab/FDSCSR .
- 25 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (3) , 1-15
Open AccessLightweight Feature De-redundancy and Self-calibration Network for Efficient Image Super-resolution
In recent years, thanks to the inherent powerful feature representation and learning abilities of the convolutional neural network (CNN), deep CNN-steered single image super-resolution approaches have achieved remarkable performance improvements. However, these methods are often accompanied by large consumption of computing and memory resources, which is difficult to be adopted in real-world application scenes. To handle this issue, we design an efficient Feature De-redundancy and Self-calibration Super-resolution network (FDSCSR). In particular, a Feature De-redundancy and Self-calibration Block (FDSCB) is proposed to reduce the repetitive feature information extracted by the model and further enhance the efficiency of the model. Then, based on FDSCB, a Local Feature Fusion Module is presented to elaborately utilize and fuse the feature information extracted by each FDSCB. Abundant experiments on benchmarks have demonstrated that our FDSCSR achieves superior performance with relatively less computational consumption and storage resource than other state-of-the-art approaches. The code is available at https://github.com/IVIPLab/FDSCSR .