Zhiyuan Zhang

Dr. Zhiyuan Zhang


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
14 January 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZZZhiyuan Zhang
Zhiyuan Zhang
JSJiadai Sun
Jiadai Sun
YDYuchao Dai
Yuchao Dai
BFBin Fan
Bin Fan
MHMingyi He
Mingyi He
3D point cloud registration is fragile to outliers, which are labeled as the points without corresponding points. To handle this problem, a widely adopted strategy is to estimate the relative pose based only on some accurate correspondences, which is achieved by building correspondences on the identified inliers or by selecting reliable ones. However, these approaches are usually complicated and time-consuming. By contrast, the virtual point-based methods learn the virtual corresponding points (VCPs) for all source points uniformly without distinguishing the outliers and the inliers. Although this strategy is time-efficient, the learned VCPs usually exhibit serious collapse degeneration due to insufficient supervision and the inherent distribution limitation. In this paper, we propose to exploit the best of both worlds and present a novel robust 3D point cloud registration framework. We follow the idea of the virtual point-based methods but learn a new type of virtual points called rectified virtual corresponding points (RCPs), which are defined as the point set with the same shape as the source and with the same pose as the target . Hence, a pair of consistent point clouds, i.e . source and RCPs, is formed by rectifying VCPs to RCPs (VRNet), through which reliable correspondences between source and RCPs can be accurately obtained. Since the relative pose between source and RCPs is the same as the relative pose between source and target , the input point clouds can be registered naturally. Specifically, we first construct the initial VCPs by using an estimated soft matching matrix to perform a weighted average on the target points. Then, we design a correction-walk module to learn an offset to rectify VCPs to RCPs, which effectively breaks the distribution limitation of VCPs. Finally, we develop a hybrid loss function to enforce the shape and geometry structure consistency of the learned RCPs and the source to provide sufficient supervision. Extensive experiments on several benchmark datasets demonstrate that our method achieves advanced registration performance and time-efficiency simultaneously. The code will be made public.

9 October 2012 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Open access
LKLars Kuhne
Lars Kuhne
JGJoachim Giesen
Joachim Giesen
ZZZhiyuan Zhang
Zhiyuan Zhang
SHSungsoo Ha
Sungsoo Ha
KMKlaus Mueller
Klaus Mueller
Color mapping and semitransparent layering play an important role in many visualization scenarios, such as information visualization and volume rendering. The combination of color and transparency is still dominated by standard alpha-compositing using the Porter-Duff over operator which can result in false colors with deceiving impact on the visualization. Other more advanced methods have also been proposed, but the problem is still far from being solved. Here we present an alternative to these existing methods specifically devised to avoid false colors and preserve visual depth ordering. Our approach is data driven and follows the recently formulated knowledge-assisted visualization (KAV) paradigm. Preference data, that have been gathered in web-based user surveys, are used to train a support-vector machine model for automatically predicting an optimized hue-preserving blending. We have applied the resulting model to both volume rendering and a specific information visualization technique, illustrative parallel coordinate plots. Comparative renderings show a significant improvement over previous approaches in the sense that false colors are completely removed and important properties such as depth ordering and blending vividness are better preserved. Due to the generality of the defined data-driven blending operator, it can be easily integrated also into other visualization frameworks.

1 August 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZZZhiyuan Zhang
Zhiyuan Zhang
YDYuchao Dai
Yuchao Dai
BFBin Fan
Bin Fan
JSJiadai Sun
Jiadai Sun
MHMingyi He
Mingyi He
Existing learning-based point feature descriptors are usually task-agnostic, which pursue describing the individual 3D point clouds as accurate as possible. However, the matching task aims at describing the corresponding points consistently across different 3D point clouds. Therefore these too accurate features may play a counterproductive role due to the inconsistent point feature representations of correspondences caused by the unpredictable noise, partiality, deformation, etc., in the local geometry. In this paper, we propose to learn a robust task-specific feature descriptor to consistently describe the correct point correspondence under interference. Born with an Encoder and a Dynamic Fusion module, our method EDFNet develops from two aspects. First, we augment the matchability of correspondences by utilizing their repetitive local structure. To this end, a special encoder is designed to exploit two input point clouds jointly for each point descriptor. It not only captures the local geometry of each point in the current point cloud by convolution, but also exploits the repetitive structure from paired point cloud by Transformer. Second, we propose a dynamical fusion module to jointly use different scale features. There is an inevitable struggle between robustness and discriminativeness of the single scale feature. Specifically, the small scale feature is robust since little interference exists in this small receptive field. But it is not sufficiently discriminative as there are many repetitive local structures within a point cloud. Thus the resultant descriptors will lead to many incorrect matches. In contrast, the large scale feature is more discriminative by integrating more neighborhood information. But it is easier to be disturbed since there is much more interference in the large receptive field. Compared with the conventional fusion strategy that handles multiple scale features equally, we analyze the consistency of them to judge the clean ones and perform larger aggregation weights on them during fusion. Then, a robust and discriminative feature descriptor is achieved by focusing on multiple clean scale features. Extensive evaluations validate that EDFNet learns a task-specific descriptor, which achieves state-of-the-art or comparable performance for robust matching of 3D point clouds.

20 February 2025 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
YDYi Ding
Yi Ding
JSJunpeng Shi
Junpeng Shi
Zai YangZai Yang
Zai Yang
ZZZhiyuan Zhang
Zhiyuan Zhang
YLYongxiang Liu
Yongxiang Liu
XLXiang Li
Xiang Li
With the rapid growth of distributed systems, deep learning-based multi-source data processing has drawn extensive attention, especially for the multi-channel networks. However, the conventional ones lack a strong theoretical foundation and the data in each channel lack necessary interactions, giving rise to insufficient robustness. Here we derive a network termed as distributed deep convolutional network (D2CN) to overcome this issue, which is explained by integrating generalized singular value decomposition (GSVD) with the principles of Hankel convolution framelet. Specifically, we employ the feature extraction capability of GSVD to perform data interactions by forward/backward propagation, where numerous inputs are designed using the common bases and reliable performance is achieved by training a shared set of right bases. We go over the network’s scalability to show its benefits in performance and robustness. Moreover, we show that the encoder-decoder scheme allows the network suitable for a wide range of inverse situations. Finally, we demonstrate the superiority of the D2CN over other fundamental networks through numerical experiments conducted on classical image denoising.

2 July 2025 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
WZWen Zheng
Wen Zheng
JSJunpeng Shi
Junpeng Shi
YLYang Li
Yang Li
AHAnd Zhitao Huang
And Zhitao Huang
ZZZhiyuan Zhang
Zhiyuan Zhang
ZLZhihui Li
Zhihui Li
Deception jamming has garnered widespread attention for threatening radar systems due to its lower energy requirement compared to traditional suppression jamming. With the rapid evolution of electronic warfare technologies, multiple-input multiple-output (MIMO) radar has demonstrated remarkable progress in countering jamming. Non-networked deception jammers, capable of generating compound deception jamming within MIMO radar's main lobe, present significant challenges. However, existing jamming recognition methods suffer from static assumptions tailored to limited jamming patterns, excessive dependence on prior knowledge, inefficacy in extracting discriminative features, and high computational cost. To overcome these limitations, we first propose the dual-domain adaptive fusion network (D $^{2}$ AF-Net). This innovative approach employs hierarchical and integrated features to alleviate recognition degradation and sensitivity to array amplitude and phase errors. Specifically, D $^{2}$ AF-Net contains two fusion-based building blocks: an intra-domain Fusion module mixing local feature and global information, and a staged fusion strategy supporting inter-domain streaming feature interactions and reducing redundant features. Our extensive experimental results based on both simulation and semi-physical datasets show that D $^{2}$ AF-Net achieves state-of-the-art performance on recognition rate, generalization ability in low JNR, and robustness for array errors while requiring fewer or comparable data processing time and interference time than competitive models.

6 December 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
ZZZhiyuan Zhang
Zhiyuan Zhang
JSJiadai Sun
Jiadai Sun
YDYuchao Dai
Yuchao Dai
DZDingfu Zhou
Dingfu Zhou
XSXibin Song
Xibin Song
MHMingyi He
Mingyi He
3-D point cloud registration in remote sensing field has been greatly advanced by deep learning-based methods, where the rigid transformation is either directly regressed from the two point clouds (correspondences-free approaches) or computed from the learned correspondences (correspondences-based approaches). Existing correspondence-free methods generally learn the holistic representation of the entire point cloud, which is fragile for partial and noisy point clouds. In this letter, we propose a correspondence-free unsupervised point cloud registration (UPCR) method from the representation separation perspective. First, we model the input point cloud as a combination of pose-invariant representation and pose-related representation. Second, the pose-related representation is used to learn the relative pose w.r.t. a “latent canonical shape” for the source and target point clouds, respectively. Third, the rigid transformation is obtained from the above two learned relative poses. Our method not only filters out the disturbance in pose-invariant representation but also is robust to partial-to-partial point clouds or noise. Experiments on benchmark datasets demonstrate that our unsupervised method achieves comparable if not better performance than state-of-the-art supervised registration methods. The source code will be made public.