Jiajun Lv | RCL Group

SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement Learning

Fri, 01 Aug 2025 00:00:00 +0000

Gaussian-LIC2 Released on arXiv

Wed, 09 Jul 2025 00:00:00 +0000

Our latest work is now available on ! This paper presents the first photo-realistic LiDAR-Inertial-Camera Gaussian Splatting SLAM system that simultaneously addresses visual quality, geometric accuracy, and real-time performance. By employing a lightweight zero-shot depth model to generate dense depth maps from sparse LiDAR measurements and RGB cues, our system enables reliable Gaussian initialization in LiDAR-blind areas and significantly improves applicability for sparse LiDAR sensors. We also demonstrate improved pose estimation under LiDAR degradation scenarios via tightly incorporating photometric constraints from the Gaussian map into the continuous-time factor graph optimization. Code and dataset will be publicly available.

Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM

Tue, 01 Jul 2025 00:00:00 +0000

Gaussian-LIC Accepted at ICRA 2025

Mon, 27 Jan 2025 00:00:00 +0000

Our work has been accepted by ICRA 2025! Gaussian-LIC is a real-time photo-realistic SLAM system that marries Gaussian Splatting with LiDAR-Inertial-Camera fusion for robust pose estimation and photo-realistic online mapping in general unbounded scenarios. Implemented purely in C++ and CUDA with carefully designed acceleration strategies, our system outperforms existing methods while maintaining real-time capability. Code is available on .

Coco-LIC: Continuous-Time Tightly-Coupled LiDAR-Inertial-Camera Odometry using Non-Uniform B-spline

Fri, 01 Sep 2023 00:00:00 +0000