Yuxuan Chen

Yuxuan Chen

Auto-generated profile, based on publicly available information

Yuxuan Chen

Department of Precision Machinery and Precision Instrumentation, University of Science and Technology of China, Hefei, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
3 May 2021 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
HCHuaian Chen
Huaian Chen
Yi JinYi Jin
Yi Jin
KXKai Xu
Kai Xu
YCYuxuan Chen
Yuxuan Chen
CZChangan Zhu
Changan Zhu
Most existing studies performed video denoising by using multiple adjacent noisy frames to recover one clean frame; however, despite achieving relatively good quality for each individual frame, these approaches may result in visual flickering when the denoised frames are considered in sequence. In this paper, instead of separately restoring each clean frame, we propose a multiframe-to-multiframe (MM) denoising scheme that simultaneously recovers multiple clean frames from consecutive noisy frames. The proposed MM denoising scheme uses a training strategy that optimizes the denoised video from both the spatial and temporal dimensions, enabling better temporal consistency in the denoised video. Furthermore, we present an MM network (MMNet), which adopts a spatiotemporal convolutional architecture that considers both the interframe similarity and single-frame characteristics. Benefiting from the underlying parallel mechanism of the MM denoising scheme, MMNet achieves a highly competitive denoising efficiency. Extensive analyses and experiments demonstrate that MMNet outperforms the state-of-the-art video denoising methods, yielding temporal consistency improvements of at least 13.3 $\%$ and running more than 2 times faster than the other methods.

8 June 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
KXKai Xu
Kai Xu
HCHuaian Chen
Huaian Chen
XTXiao Tan
Xiao Tan
YCYuxuan Chen
Yuxuan Chen
Yi JinYi Jin
Yi Jin
CZChangan Zhu
Changan Zhu
Images captured in low-light environments often suffer from issues related to dark illumination and damaged details, which results in poor visibility. To address these problems, existing methods have attempted to enhance the visibility of low-light images using convolutional neural networks (CNNs). However, due to the insufficient consideration of crucial features such as illumination and edge details, most of them yield unnatural illumination and blurry details. In this work, to fully exploit these features, we present a detailed analysis of the illumination and edge features of low-light images, observing that the frequency components of these two features are considerably different. Therefore, we explore the frequency distributions of the feature maps extracted from different layers of a CNN model and try to seek the best representation for the illumination and edge information. Based on this, we present a hierarchical feature mining network (HFMNet) that extracts illumination and edge features in different network layers. Specifically, we build a feature mining attention (FMA) module combined with a hierarchical supervised loss to mine crucial features in appropriate network layer. Since deep hierarchical supervision tends to cause overfitting, we introduce an unpaired adversarial loss for improving the generality of the enhancement model. Through extensive experiments and analysis, we demonstrate the advantages of the proposed network, which achieves the state-of-the-art performance in terms of image quality.

6 April 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YCYuxuan Chen
Yuxuan Chen
BWBen Wang
Ben Wang
QLQiongwei Li
Qiongwei Li
YZYujun Zhong
Yujun Zhong
Yi JinYi Jin
Yi Jin
CZChangan Zhu
Changan Zhu
The 3-D shape reconstruction is a hot topic in computational imaging and many related techniques have been developed. However, most of these techniques have a limited field-of-view (FOV), which results in difficulties on general application. In this article, an FOV-enlarged single-camera 3-D shape reconstruction system is proposed. By placing a saccade mirror in the light path, the proposed system generates a series of virtual cameras and reconstructs the object with multiview images. As the virtual cameras have the same resolution with the real camera, the system gets a larger FOV for reconstruction without sacrificing image resolution. Besides, compared with conventional stereovision systems, the proposed system gives a prior of postures of virtual cameras and simplifies the calibration procedure of extrinsic parameters, which makes it a compact and economical system for application. Reconstruction experiments demonstrate that the proposed system provides an FOV-enlarged and accurate 3-D shape reconstruction. Furthermore, the robustness of the system to environmental conditions is also verified by real-life experiments.

2 March 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
BWBen Wang
Ben Wang
Yi JinYi Jin
Yi Jin
YCYuxuan Chen
Yuxuan Chen
ZSZheng Sun
Zheng Sun
MDMinghui Duan
Minghui Duan
JZJinjin Zheng
Jinjin Zheng
3-D reconstruction of a moving object is a hotpot in structured-light research. However, large-scale motion causes sparse point cloud density and low reconstruction accuracy in a conventional structured-light system (SLS) because the field-of-view (FOV) of the camera is enlarged to prevent object loss. In this article, we propose a gaze tracking 3-D reconstruction system (GT3DRS), which utilizes a saccade mirror to construct a dynamic relationship between the camera and projector for an object with large-scale motion. In the GT3DRS, the real-time position of the moving object is obtained using a tracking algorithm, and a saccade mirror is adopted to keep the moving object constantly located at the center of the FOV according to the position, which enables the camera’s FOV to compactly cover the object. The GT3DRS increases the resolution of the object, effectively enhancing the point cloud density of the reconstructed 3-D profile and improving the reconstruction accuracy. In addition, a new calibration framework is established for the proposed GT3DRS, which reduces the system errors by introducing an assumption of nonideal installation and improves calibration efficiency by building an external parameter transformation model (EPTM) to describe the dynamic relationship. Experimental results verify that the point cloud density is increased by 5.2 times, and the reconstruction accuracy is improved by an average of 10.6 times compared with a conventional SLS. Moreover, the tracking reconstruction video sequence reaches 15 fps.

6 May 2022
Verified
Conference Paper
Closed access
PDF file
RWRuijie Wang
Ruijie Wang
YCYuxuan Chen
Yuxuan Chen
ZZZhengtao Zou
Zhengtao Zou
This paper introduced a method to generate handwritten digit images by using the Generative Adversarial Networks model. Alternating loss and unstable accuracy were persistent problems during the training process. Human handwritten digit image generation plays a crucial role in criminal investigation and machine learning. There are many excellent and effective ordinary deep networks in machine learning programs for recognizing different pieces of images. However, only a few models can be used to construct new patterns. The experiment used Generative Adversarial Networks as the core algorithm to generate data that look like human-written digits. A Convolutional Neural Networks model is used as Discriminator to evaluate whether an image is genuine or created. The inverse convolutional layers in the code turn input into a two-dimensional pixel values picture. The MNIST provides as much as 60,000 data samples for training the program, where thousands of handwritten single digits, between 0 and 9, are displayed by 28*28 pixels images in greyscale. The pictures created by the algorithm initially looked blurry. But after thousands of training steps, the statistics appeared much more realistic. With more iterations carried out, the output images became more and more distinguishable.

24 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
YCYu-Xuan Chen
Yu-Xuan Chen
DFDagan Feng
Dagan Feng
HSHong-Bin Shen
Hong-Bin Shen
Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer networks show an improved performance on clean images but will not achieve satisfactory performance on noisy images due to its heavy reliance on pixel value comparations. To handle such challenging applications, we report a new unsupervised difference learning (UDL) strategy and apply it to rigid image alignment. UDL exploits the quantitative properties of regression tasks and converts the original unsupervised problem to pseudo supervised problem. Under the new UDL-based image alignment pipeline, rotation can be accurately estimated on both clean and noisy images and translations can then be easily solved. Experimental results on both nature and cryo-EM images demonstrate the efficacy of our UDL-based unsupervised rigid image alignment method.