5 papers
Dynamic Visual SLAM using a General 3D Prior
Xingguang Zhong, Liren Jin, Marija PopoviÄ +2
Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. Ho…
PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map
Yue Pan, Xingguang Zhong, Liren Jin +4
Robots benefit from high-fidelity reconstructions of their environment, which should be geometrically accurate and photorealistic to support downstream tasks. While this can be ach…
Globally Consistent RGB-D SLAM with 2D Gaussian Splatting
Xingguang Zhong, Yue Pan, Liren Jin +3
Recently, 3D Gaussian splatting-based RGB-D SLAM displays remarkable performance of high-fidelity 3D reconstruction. However, the lack of depth rendering consistency and efficient…
DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction
Sicong Pan, Liren Jin, Xuying Huang +3
Active object reconstruction is crucial for many robotic applications. A key aspect in these scenarios is generating object-specific view configurations to obtain informative measu…
ActiveGS: Active Scene Reconstruction Using Gaussian Splatting
Liren Jin, Xingguang Zhong, Yue Pan +3
Robotics applications often rely on scene reconstructions to enable downstream tasks. In this work, we tackle the challenge of actively building an accurate map of an unknown scene…