PAPL-SLAM: Principal Axis-Anchored Monocular Point-Line SLAM

Guanghao Li*, Yu Cao*, Qi Chen*, Xin Gao, Yifan Yang, Jian Pu

Project

• PAPL-SLAM is a point-line SLAM system that efficiently integrates line structural information and optimization by anchoring lines to a principal axis, reducing the number of parameters, and utilizing probabilistic data association, enabling robust, rapid, and accurate mapping and tracking in both indoor and outdoor environments.

Multi-LIO: A Lightweight Multiple LiDAR-Inertial Odometry System

Qi Chen*, Guanghao Li*, Xiangyang Xue, Jian Pu

Project

• Multi-LIO is a real-time, computationally efficient multiple LiDAR-inertial odometry system that enhances accuracy and scalability, using parallel state updates, voxelized maps, and point-wise uncertainty estimation to improve scan-to-map registration in large-scale, complex environments.

VPL-SLAM: A Vertical Line Supported Point Line Monocular SLAM System

Qi Chen, Yu Cao, Jiawei Hou, Guanghao Li, Bo Chen, Xiangyang Xue, Hong Lu, Jian Pu

Project

• VPL-SLAM is a monocular SLAM system that improves localization and mapping in complex environments by integrating structural vertical lines with point-line features.

Constrained Gaussian Splatting via Implicit TSDF Hash Grid for Dense RGB-D SLAM

Guanghao Li, Qi Chen, Sijia Hu, Yuxiang Yan, Jian Pu

Project

• FusionMap is an advanced SLAM system that combines explicit 3DGS and implicit NeRF representations to improve surface reconstruction accuracy. By addressing the limitations of traditional 3DGS, FusionMap achieves up to 30 times faster processing and a 38% accuracy boost over conventional methods. This innovation sets new standards for real-time 3D mapping and localization, enabling next-generation applications in virtual environments, autonomous navigation, and dynamic scene reconstruction.

EC-SLAM: Real-time Dense Neural RGB-D SLAM System with Effectively Constrained Global Bundle Adjustment

Guanghao Li*, Qi Chen*, Yuxiang Yan, Jian Pu

Project

• EC-SLAM is a real-time dense RGB-D SLAM system that leverages Neural Radiance Fields (NeRF) for enhanced pose optimization, using sparse parametric encodings, TSDF, and a globally constrained Bundle Adjustment strategy to improve tracking accuracy and reconstruction performance in real-time.

JointDeblur-GS: Joint Blur-Aware Gaussian Splatting

Sijia Hu, Peng Chen, Xinxiao Wang, Luyue Sun, Guanghao Li, Hongyu Wang, Jian Pu

Project

• JointDeblur-GS is a joint optimization framework that integrates a blur-aware network to enhance image quality and optimize 3D Gaussian parameters for effective motion blur removal and multiview consistency, achieving superior reconstruction quality with real-time performance.

Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection

Guo jiasheng, Xin Gao, Yuxiang Yan, Guanghao Li, Jian Pu

Project

• Dark-ISP is a lightweight and self-adaptive Image Signal Processing (ISP) plugin designed to improve low-light object detection. Unlike previous methods that either use RAW-RGB images with information loss or complex frameworks, Dark-ISP processes Bayer RAW images directly in dark environments. Its key innovations include deconstructing conventional ISP pipelines into linear and nonlinear sub-modules optimized for task-driven losses, and a self-boosting strategy that enhances cooperation between sub-modules.