Wencheng Li

Wencheng Li

Auto-generated profile, based on publicly available information

Wencheng Li

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
30 November 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
WLWencheng Li
Wencheng Li
GCGang Chen
Gang Chen
Yi ChangYi Chang
Yi Chang
Single image de-raining is an emerging paradigm for many outdoor computer vision applications since rain streaks can significantly degrade the visibility and render the function compromised. The introduction of deep learning (DL) has brought about substantial advancement on de-raining methods. However, most existing DL-based methods use single homogeneous network architecture to generate de-rained images in a general image restoration manner, ignoring the discrepancy between rain location detection and rain intensity estimation. We find that this discrepancy would cause feature interference and representation ability degradation problems which significantly affect de-raining performance. In this paper, we propose a novel heterogeneous de-raining architecture aiming to decouple rain location detection and rain intensity estimation (DLINet). For these two subtasks, we provide dedicated network structures according to their differential properties to meet their respective performance requirements. To coordinate the decoupled subnetworks, we develop a high-order collaborative network learning the dynamic inter-layer interactions between rain location and intensity. To effectively supervise the decoupled subnetworks during training, we propose a novel training strategy that imposes task-oriented supervision using the label learned via joint training. Extensive experiments on synthetic datasets and real-world rainy scenes demonstrate that the proposed method has great advantages over existing state-of-the-art methods.

3 August 2020 in Applied Optics
Verified
Journal Article
Closed access
WLWen-Cheng Li
Wen-Cheng Li
QYQiurong Yan
Qiurong Yan
YGYan-Qiu Guan
Yan-Qiu Guan
SYSheng-Tao Yang
Sheng-Tao Yang
CPCong Peng
Cong Peng
ZFZhe-Yu Fang
Zhe-Yu Fang
The combination of single-pixel-imaging and single-photon-counting technology can achieve ultrahigh-sensitivity photon-counting imaging. However, its applications in high-resolution and real-time scenarios are limited by the long sampling and reconstruction time. Deep-learning-based compressive sensing provides an effective solution due to its ability to achieve fast and high-quality reconstruction. This paper proposes a sampling and reconstruction integrated neural network for single-photon-counting compressive imaging. To effectively remove the blocking artefact, a subpixel convolutional layer is jointly trained with a deep reconstruction network to imitate compressed sampling. By modifying the forward and backward propagation of the network, the first layer is trained into a binary matrix, which can be applied to the imaging system. An improved deep-reconstruction network based on the traditional Inception network is proposed, and the experimental results show that its reconstruction quality is better than existing deep-learning-based compressive sensing reconstruction algorithms.

5 November 2009 in Electronics Letters
Verified
Journal Article
Closed access
YZY. Zhang
Y. Zhang
WLW. Li
W. Li
A feedforward neural-network is proposed with hidden-layer neurons activated by Gegenbauer orthogonal functions. Compared with conventional back-propagation training algorithms, a weights-direct-determination method is proposed to determine the neural-network weights directly, which avoids a lengthy iterative-training procedure. Computer simulations further substantiate the efficacy of such a Gegenbauer orthogonal basis neural network.