5 papers
RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos
Wenting Wang, Jiaxin Guo, Wenzhen Dong +3
In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assumptions. In this work, we propos…
InvariantCloud: A Globally Invariant, Uniquely Indexed Point Cloud Framework for Robust 6-DoF Tactile Pose Tracking
Pengfei Ye, Yuxiang Ma, Yi Zhou +3
Recent advances in imitation learning and vision-language models highlight the need for high-fidelity tactile perception, with 6-DoF tactile object pose estimation providing a cruc…
SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
Jiaxin Guo, Tongfan Guan, Wenzhen Dong +5
Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel G…
Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video
Jiaxin Guo, Wenzhen Dong, Tianyu Huang +5
Reconstructing 3D scenes from monocular surgical videos can enhance surgeon's perception and therefore plays a vital role in various computer-assisted surgery tasks. However, achie…
Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction
Jiaxin Guo, Jiangliu Wang, Di Kang +3
Real-time 3D reconstruction of surgical scenes plays a vital role in computer-assisted surgery, holding a promise to enhance surgeons' visibility. Recent advancements in 3D Gaussia…