activity
20192021
most citedHR-Depth: High Resolution Self-Supervised Monocular Depth Estimation

24 citations · 49 across the 6 of their papers we have counts for

collaborators

8 papers

cs.CV20214 cited

Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds

Xuemeng Yang, Hao Zou, Xin Kong +5

Outdoor scene completion is a challenging issue in 3D scene understanding, which plays an important role in intelligent robotics and autonomous driving. Due to the sparsity of LiDA…

cs.CV20212 cited

SSC: Semantic Scan Context for Large-Scale Place Recognition

Lin Li, Xin Kong, Xiangrui Zhao +2

Place recognition gives a SLAM system the ability to correct cumulative errors. Unlike images that contain rich texture features, point clouds are almost pure geometric information…

cs.RO20213 cited

SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure

Lin Li, Xin Kong, Xiangrui Zhao +4

LiDAR-based SLAM system is admittedly more accurate and stable than others, while its loop closure detection is still an open issue. With the development of 3D semantic segmentatio…

cs.CV202024 cited

HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation

Xiaoyang Lyu, Liang Liu, Mengmeng Wang +5

Self-supervised learning shows great potential in monoculardepth estimation, using image sequences as the only source ofsupervision. Although people try to use the high-resolutioni…

cs.CV202010 cited

FlowMOT: 3D Multi-Object Tracking by Scene Flow Association

Guangyao Zhai, Xin Kong, Jinhao Cui +2

Most end-to-end Multi-Object Tracking (MOT) methods face the problems of low accuracy and poor generalization ability. Although traditional filter-based methods can achieve better…

cs.CV2020

F-Siamese Tracker: A Frustum-based Double Siamese Network for 3D Single Object Tracking

Hao Zou, Jinhao Cui, Xin Kong +4

This paper presents F-Siamese Tracker, a novel approach for single object tracking prominently characterized by more robustly integrating 2D and 3D information to reduce redundant…