5 papers
ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control
Haosen Wang, Zhenyang Li, Yinqiang Zhang +9
Zero-shot object navigation has advanced rapidly with open-vocabulary detectors, image--text models, and language-guided exploration. However, even after current methods detect a p…
Semantic2D: Enabling Semantic Scene Understanding with 2D Lidar Alone
Zhanteng Xie, Yipeng Pan, Yinqiang Zhang +2
This article presents a complete semantic scene understanding workflow using only a single 2D lidar. This fills the gap in 2D lidar semantic segmentation, thereby enabling the reth…
DensifyBeforehand: LiDAR-assisted Content-aware Densification for Efficient and Quality 3D Gaussian Splatting
Phurtivilai Patt, Leyang Huang, Yinqiang Zhang +1
This paper addresses the limitations of existing 3D Gaussian Splatting (3DGS) methods, particularly their reliance on adaptive density control, which can lead to floating artifacts…
GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction
Yuhan Xie, Yixi Cai, Yinqiang Zhang +2
This research tackles the challenge of real-time active view selection and uncertainty quantification on visual quality for active 3D reconstruction. Visual quality is a critical a…
Signage-Aware Exploration in Open World using Venue Maps
Chang Chen, Liang Lu, Lei Yang +4
Current exploration methods struggle to search for shops or restaurants in unknown open-world environments due to the lack of prior knowledge. Humans can leverage venue maps that o…