Jiayuan Du
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiayuan Du has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Qijun Chen
Tongji University
9 shared publications - Chengju Liu
Tongji University
6 shared publications - Liuyi Wang
Tongji University
3 shared publications - Rui Fan
College of Electronics and Information Engineering, Tongji University, Shanghai, China
3 shared publications - Xianghui Pan
Tongji University
3 shared publications - Yuebing Song
Tongji University
3 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (22) , 34403-34416
TJBe-GS: Rigid Trajectory-Guided Bézier Gaussian Splatting for RGB-D Dynamic Reconstruction
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (22) , 34403-34416
TJBe-GS: Rigid Trajectory-Guided Bézier Gaussian Splatting for RGB-D Dynamic Reconstruction
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 51 (4) , 3710-3720
MaRIne: An Underwater Monocular Real-Time Object Detection and Geometric Estimation Framework Based on Motion Inversion
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 51 (4) , 3710-3720
MaRIne: An Underwater Monocular Real-Time Object Detection and Geometric Estimation Framework Based on Motion Inversion
- 10 September 2026
- Published by Springer Nature
- p. 178-195
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
- 10 September 2026
- Published by Springer Nature
- p. 178-195
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 4353-4360
BEVDrive-E2E: Imitation With Bird's Eye View Perception for Interpretable End-to-End Autonomous Driving
Imitation learning (IL) for end-to-end autonomous driving (E2E-AD) has made great progress recently in the closed-loop evaluation of the CARLA simulator. However, the causal confusion remains an open problem. To address this issue, we propose the BEVDrive-E2E to explore the interpretability of the end-to-end model by using visual abstractions in bird's eye view (BEV). We design a hybrid BEV fusion module (HBFM) that combines the feature aggregation capabilities of CNN and transformer in both local and global areas. To fully exploit the benefits of BEV representation, we perform BEV detection and segmentation to form a unified semantic BEV map and adopt a two-stage training schedule. We leverage the transformer decoder to predict the sequential path points in an autoregressive manner. Our proposed approach shows the state-of-the-art (SOTA) performance on both CARLA leaderboard 1.0 and leaderboard 2.0.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 4353-4360
BEVDrive-E2E: Imitation With Bird's Eye View Perception for Interpretable End-to-End Autonomous Driving
Imitation learning (IL) for end-to-end autonomous driving (E2E-AD) has made great progress recently in the closed-loop evaluation of the CARLA simulator. However, the causal confusion remains an open problem. To address this issue, we propose the BEVDrive-E2E to explore the interpretability of the end-to-end model by using visual abstractions in bird's eye view (BEV). We design a hybrid BEV fusion module (HBFM) that combines the feature aggregation capabilities of CNN and transformer in both local and global areas. To fully exploit the benefits of BEV representation, we perform BEV detection and segmentation to form a unified semantic BEV map and adopt a two-stage training schedule. We leverage the transformer decoder to predict the sequential path points in an autoregressive manner. Our proposed approach shows the state-of-the-art (SOTA) performance on both CARLA leaderboard 1.0 and leaderboard 2.0.
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 3550-3557
A&B-LO: Continuous-Time LiDAR Odometry With Adaptive Non-Uniform B-Spline Trajectory Representation
LiDAR odometry, fused by inertial measurement units (IMU), is an essential task in robotics navigation. Unlike the mainstream methods compensate the motion distortion of LiDAR data by high frequency inertial sensors, this letter deals with the distortion with continuous-time trajectory representation, and achieved competitive performance against state-of-the-art. We propose a compact framework of LiDAR odometry with adaptive non-uniform B-spline trajectory representation to formulate it as continuous-time estimation problem. We deploy point-to-plane registration and pseudo-velocity smoothing constraints to fully utilize geometric and kinematic information of odometry. For faster convergence of optimization, analytical Jacobian of constraints is derived to solve the non-linear least squares minimization. For more efficient B-spline representation, an adaptive knot spacing technique is proposed to adjust the time interval of control poses of spline. Extensive experiments on public and realistic datasets demonstrate validation and efficiency of our system compared with other LiDAR or LiDAR-inertial methods.
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 3550-3557
A&B-LO: Continuous-Time LiDAR Odometry With Adaptive Non-Uniform B-Spline Trajectory Representation
LiDAR odometry, fused by inertial measurement units (IMU), is an essential task in robotics navigation. Unlike the mainstream methods compensate the motion distortion of LiDAR data by high frequency inertial sensors, this letter deals with the distortion with continuous-time trajectory representation, and achieved competitive performance against state-of-the-art. We propose a compact framework of LiDAR odometry with adaptive non-uniform B-spline trajectory representation to formulate it as continuous-time estimation problem. We deploy point-to-plane registration and pseudo-velocity smoothing constraints to fully utilize geometric and kinematic information of odometry. For faster convergence of optimization, analytical Jacobian of constraints is derived to solve the non-linear least squares minimization. For more efficient B-spline representation, an adaptive knot spacing technique is proposed to adjust the time interval of control poses of spline. Extensive experiments on public and realistic datasets demonstrate validation and efficiency of our system compared with other LiDAR or LiDAR-inertial methods.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 2865-2872
TerrFlat: Physics-Driven Geometry Representation for Structure-Aware Freespace Detection
Freespace detection in autonomous driving is limited by the lack of explicit geometric modeling, hindering generalization across complex terrains. Existing approaches are predominantly data-driven and neglect the physical structure of drivable surfaces. We propose Terrain Flat (TerrFlat), a physics-driven geometric representation that models road surfaces along three interpretable dimensions: lateral smoothness, longitudinal consistency, and vertical deviation. TerrFlat is constructed through geometric reasoning and projected into pixel-aligned maps via a differentiable projection, ensuring geometric–visual consistency. Building on this representation, we introduce a symmetric feature fusion module (SFFM) to integrate TerrFlat with visual features through bidirectional recalibration, improving semantic discrimination and boundary localization. Together, TerrFlat and SFFM form TerrFlat-Seg, a unified framework for physics-aware freespace perception. Experiments on KITTI-Road, Semantic-KITTI, and the off-road ORFD datasets demonstrate consistent improvements over existing baselines. Real-world validation on an automated guided vehicle platform further confirms the robustness of our approach.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (3) , 2865-2872
TerrFlat: Physics-Driven Geometry Representation for Structure-Aware Freespace Detection
Freespace detection in autonomous driving is limited by the lack of explicit geometric modeling, hindering generalization across complex terrains. Existing approaches are predominantly data-driven and neglect the physical structure of drivable surfaces. We propose Terrain Flat (TerrFlat), a physics-driven geometric representation that models road surfaces along three interpretable dimensions: lateral smoothness, longitudinal consistency, and vertical deviation. TerrFlat is constructed through geometric reasoning and projected into pixel-aligned maps via a differentiable projection, ensuring geometric–visual consistency. Building on this representation, we introduce a symmetric feature fusion module (SFFM) to integrate TerrFlat with visual features through bidirectional recalibration, improving semantic discrimination and boundary localization. Together, TerrFlat and SFFM form TerrFlat-Seg, a unified framework for physics-aware freespace perception. Experiments on KITTI-Road, Semantic-KITTI, and the off-road ORFD datasets demonstrate consistent improvements over existing baselines. Real-world validation on an automated guided vehicle platform further confirms the robustness of our approach.
- Top Cited Papers
- 20 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 314
SAM-LAD: Segment Anything Model meets zero-shot logic anomaly detection
- 20 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 314
Top Cited PapersSAM-LAD: Segment Anything Model meets zero-shot logic anomaly detection
- 7 October 2023
- Published by Springer Nature
- p. 323-356
Bird’s Eye View Perception for Autonomous Driving
- 7 October 2023
- Published by Springer Nature
- p. 323-356
Bird’s Eye View Perception for Autonomous Driving
- 18 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (2) , 1511-1520
Freespace Optical Flow Modeling for Automated Driving
Optical flow and disparity are two informative visual features for autonomous driving perception. They have been used for a variety of applications, such as obstacle and lane detection. The concept of “U-V-Disparity” has been widely explored in the literature, while its counterpart in optical flow has received relatively little attention. Traditional motion analysis algorithms estimate optical flow by matching correspondences between two successive video frames, which limits the full utilization of environmental information and geometric constraints. Therefore, we propose a novel strategy to model optical flow in the collision-freespace (also referred to as drivable area or simply freespace) for intelligent vehicles, with the full utilization of geometry information in a 3-D driving environment. We provide explicit representations of optical flow and deduce the quadratic relationship between the optical flow component and the vertical coordinate. Through extensive experiments on several public datasets, we demonstrate the high accuracy and robustness of our model. In addition, our proposed freespace optical flow model boasts a diverse array of applications within the realm of automated driving, providing a geometric constraint in freespace detection, vehicle localization, and more. We have made our source code publicly available at https://mias.group/FSOF .
- 18 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (2) , 1511-1520
Freespace Optical Flow Modeling for Automated Driving
Optical flow and disparity are two informative visual features for autonomous driving perception. They have been used for a variety of applications, such as obstacle and lane detection. The concept of “U-V-Disparity” has been widely explored in the literature, while its counterpart in optical flow has received relatively little attention. Traditional motion analysis algorithms estimate optical flow by matching correspondences between two successive video frames, which limits the full utilization of environmental information and geometric constraints. Therefore, we propose a novel strategy to model optical flow in the collision-freespace (also referred to as drivable area or simply freespace) for intelligent vehicles, with the full utilization of geometry information in a 3-D driving environment. We provide explicit representations of optical flow and deduce the quadratic relationship between the optical flow component and the vertical coordinate. Through extensive experiments on several public datasets, we demonstrate the high accuracy and robustness of our model. In addition, our proposed freespace optical flow model boasts a diverse array of applications within the realm of automated driving, providing a geometric constraint in freespace detection, vehicle localization, and more. We have made our source code publicly available at https://mias.group/FSOF .
- Open Access
Freespace Optical Flow Modeling for Automated Driving
Optical flow and disparity are two informative visual features for autonomous driving perception. They have been used for a variety of applications, such as obstacle and lane detection. The concept of "U-V-Disparity" has been widely explored in the literature, while its counterpart in optical flow has received relatively little attention. Traditional motion analysis algorithms estimate optical flow by matching correspondences between two successive video frames, which limits the full utilization of environmental information and geometric constraints. Therefore, we propose a novel strategy to model optical flow in the collision-free space (also referred to as drivable area or simply freespace) for intelligent vehicles, with the full utilization of geometry information in a 3D driving environment. We provide explicit representations of optical flow and deduce the quadratic relationship between the optical flow component and the vertical coordinate. Through extensive experiments on several public datasets, we demonstrate the high accuracy and robustness of our model. Additionally, our proposed freespace optical flow model boasts a diverse array of applications within the realm of automated driving, providing a geometric constraint in freespace detection, vehicle localization, and more. We have made our source code publicly available at https://mias.group/FSOF.
Open AccessFreespace Optical Flow Modeling for Automated Driving
Optical flow and disparity are two informative visual features for autonomous driving perception. They have been used for a variety of applications, such as obstacle and lane detection. The concept of "U-V-Disparity" has been widely explored in the literature, while its counterpart in optical flow has received relatively little attention. Traditional motion analysis algorithms estimate optical flow by matching correspondences between two successive video frames, which limits the full utilization of environmental information and geometric constraints. Therefore, we propose a novel strategy to model optical flow in the collision-free space (also referred to as drivable area or simply freespace) for intelligent vehicles, with the full utilization of geometry information in a 3D driving environment. We provide explicit representations of optical flow and deduce the quadratic relationship between the optical flow component and the vertical coordinate. Through extensive experiments on several public datasets, we demonstrate the high accuracy and robustness of our model. Additionally, our proposed freespace optical flow model boasts a diverse array of applications within the realm of automated driving, providing a geometric constraint in freespace detection, vehicle localization, and more. We have made our source code publicly available at https://mias.group/FSOF.