Weijian Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Weijian Zhang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Lizhuang Ma
Shanghai Jiao Tong University, Shanghai, China
3 shared publications - Xin Tan
East China Normal University
3 shared publications - Yuan Xie
The Hong Kong University of Science and Technology, Hong Kong, Hong Kong
3 shared publications - Zhizhong Zhang
East China Normal University
2 shared publications - Haichuan Song
East China Normal University, Shanghai, China
1 shared publication - Jingyu Gong
East China Normal University, Shanghai, China
1 shared publication
Latest Publications
- 11 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4004-4016
Decoupling 3-D Point Cloud Attributes for Semantic Segmentation via Real-World Prior Exploitation
Point cloud semantic segmentation, which involves assigning a category for each point, is a crucial task in autonomous driving and intelligent transportation systems. Due to the inherently unordered and irregular nature of point clouds, learning robust features that accurately capture real-world distributions from point coordinates and other attributes remains challenging. Following the pioneering work of PointNet, current 3D deep neural networks process point coordinates alongside other attributes without fully exploiting the implicit class prior information embedded in spatial information. In this work, we first conduct a pilot study to evaluate how current 3D networks utilize point coordinates and validate the presence of implicit class priors within them. Subsequently, we design a robust Position-to-Physics (P2P) fusion strategy that learns adaptive weights to dynamically incorporate implicit class priors present in point coordinates into point features. Moreover, we design a dual-branch network architecture and propose a triplet loss to further enhance the adaptive fusion process. Extensive experiments demonstrate that decoupling position attributes from physics attributes facilitates the extraction and utilization of implicit class priors. Our proposed modules consistently improve segmentation performance across various networks and datasets, demonstrating their generalizability and effectiveness.
- 11 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4004-4016
Decoupling 3-D Point Cloud Attributes for Semantic Segmentation via Real-World Prior Exploitation
Point cloud semantic segmentation, which involves assigning a category for each point, is a crucial task in autonomous driving and intelligent transportation systems. Due to the inherently unordered and irregular nature of point clouds, learning robust features that accurately capture real-world distributions from point coordinates and other attributes remains challenging. Following the pioneering work of PointNet, current 3D deep neural networks process point coordinates alongside other attributes without fully exploiting the implicit class prior information embedded in spatial information. In this work, we first conduct a pilot study to evaluate how current 3D networks utilize point coordinates and validate the presence of implicit class priors within them. Subsequently, we design a robust Position-to-Physics (P2P) fusion strategy that learns adaptive weights to dynamically incorporate implicit class priors present in point coordinates into point features. Moreover, we design a dual-branch network architecture and propose a triplet loss to further enhance the adaptive fusion process. Extensive experiments demonstrate that decoupling position attributes from physics attributes facilitates the extraction and utilization of implicit class priors. Our proposed modules consistently improve segmentation performance across various networks and datasets, demonstrating their generalizability and effectiveness.
- 22 February 2026
- Published by Elsevier in Neural Networks
- Vol. 200, 108767
From sparse semantics to rich instances: Empowering label-efficient LiDAR panoptic segmentation via geometric priors
- 22 February 2026
- Published by Elsevier in Neural Networks
- Vol. 200, 108767
From sparse semantics to rich instances: Empowering label-efficient LiDAR panoptic segmentation via geometric priors
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1386-1394
PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1386-1394
Open AccessPFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion