Xinchun Ji — accepted AI-conference papers

2026

IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting

Wei Long, Haifeng Wu, Shiyin Jiang, Jinhua Zhang, Xinchun Ji, Shuhang Gu

CVPR 2026

Generalizable 3D Gaussian Splatting aims to directly predict Gaussian parameters using a feed-forward network for scene reconstruction. Among these parameters, Gaussian means are particularly difficult to predict, so depth is usually estimated first and then unprojected to obtain the Gaussian sphere

Cited by 0 Source ↗code ↗Scholar ↗

2025

GLIC-Calib: Targetless and One-Shot Spatial-Temporal Calibration of LiDAR-IMU-Camera for Ground Vehicles

Hang Zhao, Xinchun Ji, Dongyan Wei

IROS 2025

Accurate spatial-temporal parameters of LiDAR, IMU and camera, including extrinsic parameter and time offset, is the key to ensure multi-sensor fusion performance for ground vehicles. Compared with target-based calibration method, targetless method does not need artificial targets which is more conv

Cited by 1 Source ↗Scholar ↗