We propose LowRankOcc to address spatial redundancy in 3D semantic occupancy prediction, leveraging the inherent low-rank property of occupancy data.
Structure-aware Cross-Modal Transformer for Depth Completion Linqing Zhao, Yi Wei, Jiaxin Li, Jie Zhou, Jiwen Lu# IEEE Transactions on Image Processing (TIP), 2024.
We disentangle the hierarchical 3D scene-level structure from the RGB-D input and construct a pathway to make sharp depth boundaries and object shape outlines accessible to 2D features.
SPTR: Structure-Preserving Transformer for Unsupervised Indoor Depth Completion Linqing Zhao, Wenzhao Zheng, Yueqi Duan, Jie Zhou, Jiwen Lu# IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023.
We propose to reformulate depth completion as the process of 3D structure generation, where the generated structure should recover the complete scene and also consist with the known partial structure.
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving Yi Wei*, Linqing Zhao*, Wenzhao Zheng,
Zheng Zhu,
Jie Zhou ,
Jiwen Lu# IEEE International Conference on Computer Vision (ICCV), 2023
We design a pipeline to generate dense occupancy ground truths without expensive occupancy annotations, which enables the training of more dense 3D occupancy prediction models.
Dense Hybrid Proposal Modulation for Lane Detection
Yuejian Wu,
Linqing Zhao,
Jiwen Lu,
Haibin Yan# IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023.
We densely modulate all proposals to generate topologically and spatially high-quality lane predictions with discriminative representations.
We propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras.
Learning Hybrid Semantic Affinity for Point Cloud Segmentation
Zhanjie Song,
Linqing Zhao,
Jie Zhou#
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021.
We present a hybrid semantic affinity learning method (HSA) to capture and leverage the dependencies of categories for 3D semantic segmentation, which aims to learn the label dependencies between 3D points from a hybrid perspective.
Similarity-Aware Fusion Network for 3D Semantic Segmentation Linqing Zhao,
Jiwen Lu#,
Jie Zhou IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021.
We propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation.
Honors
Academic Scholarship of Tianjin University: 2017, 2019, 2022
First Prize of the Doctoral Student Academic Forum of the School of EIE, Tianjin University: 2022
Academic Services
Conference Reviewer: ICRA, IROS, ACM MM, ICME, ICASSP