Hong Zhang

Latest

• A Tightly-Coupled and Keyframe-Based Visual-Inertial-Lidar Odometry System for UGVs With Adaptive Sensor Reliability Evaluation
• Cloud-edge Collaborative Submap-based VSLAM using Implicit Representation Transmission
• Edge-Assisted Multi-Robot Visual-Inertial SLAM With Efficient Communication
• Efficient Object Rearrangement via Multi-view Fusion
• NPR: Nocturnal Place Recognition Using Nighttime Translation in Large-Scale Training Procedures
• PISR: Polarimetric Neural Implicit Surface Reconstruction for Textureless and Specular Objects
• Visual Object Tracking with Mutual Affinity Aligned to Human Intuition
• Wireless Localization and Formation Control with Asynchronous Agents
• Cloud Learning-based Meets Edge Model-based: Robots Don't Need to Build All the Submaps dItself
• Condition-invariant and compact visual place description by convolutional autoencoder
• Graspgpt: Leveraging semantic knowledge from a large language model for task-oriented grasping
• Hybrid Cross-Transformer-KPConv for Point Cloud Segmentation
• IGICP: Intensity and geometry enhanced LiDAR odometry
• Large-scale graph sinkhorn distance approximation for resource-constrained devices
• Multi-Scale Point Octree Encoding Network for Point Cloud Based Place Recognition
• Robot person following under partial occlusion
• Robust Data Association Against Detection Deficiency for Semantic SLAM
• Rumination Meets VSLAM: You Do Not Need to Build All the Submaps in Realtime
• Task-oriented grasp prediction with visual-language inputs
• VI-HSO: Hybrid Sparse Monocular Visual-Inertial Odometry
• Keyframe Selection with Information Occupancy Grid Model for Long-term Data Association
• Deep Tri-Training for Semi-Supervised Image Segmentation
• Fire together wire together: A dynamic pruning approach with self-supervised mask prediction
• NDD: A 3D Point Cloud Descriptor Based on Normal Distribution for Loop Closure Detection
• Perspective phase angle model for polarimetric 3d reconstruction
• Relationship Oriented Semantic Scene Understanding for Daily Manipulation Tasks
• Robust UWB indoor localization for NLOS scenes via learning spatial-temporal features
• Deep snapshot HDR reconstruction based on the polarization camera
• Deeprelativefusion: Dense monocular slam using single-image relative depth prediction
• Dense point cloud map construction based on stereo VINS for mobile vehicles
• Dynamic strategy of keyframe selection with pd controller for vslam systems
• Mapping While Following: 2D LiDAR SLAM in Indoor Dynamic Environments with a Person Tracker
• Resilient indoor localization system based on UWB and visual--inertial sensors for complex environments
• Robust Improvement in 3D Object Landmark Inference for Semantic Mapping
• Robustness improvement of using pre-trained network in visual odometry for on-road driving
• Semantic visual SLAM in dynamic environment
• UVIP: Robust UWB aided visual-inertial positioning system for complex indoor environments
• FastORB-SLAM: A fast ORB-SLAM method with Coarse-to-Fine descriptor independent keypoint matching
• Learning representations from skeletal self-similarities for cross-view action recognition
• Real-time 3-D semantic scene parsing with LiDAR sensors