6 papers
STAR-VLM: Spatiotemporal Grounding Vision-Language Models for Motion and Velocity Estimation via Automotive Radar Supervision
Pou-Chun Kung, Aryaman Rao, Utkrisht Sahai +4
Vision-language models (VLMs) are emerging as a key component of embodied intelligence, with growing applications in auto-labeling and end-to-end autonomous driving. However, exist…
HumanSplatHMR: Closing the Loop Between Human Mesh Recovery and Gaussian Splatting Avatar
Yeheng Zong, Pou-Chun Kung, Yike Pan +4
Accurately recovering human pose and appearance from video is an essential component of scene reconstruction, with applications to motion capture, motion prediction, virtual realit…
RadarSplat-RIO: Indoor Radar-Inertial Odometry with Gaussian Splatting-Based Radar Bundle Adjustment
Pou-Chun Kung, Yuan Tian, Zhengqin Li +4
Radar is more resilient to adverse weather and lighting conditions than visual and Lidar simultaneous localization and mapping (SLAM). However, most radar SLAM pipelines still rely…
LiHi-GS: LiDAR-Supervised Gaussian Splatting for Highway Driving Scene Reconstruction
Pou-Chun Kung, Xianling Zhang, Katherine A. Skinner +1
Photorealistic 3D scene reconstruction plays an important role in autonomous driving, enabling the generation of novel data from existing datasets to simulate safety-critical scena…
SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting
Advaith V. Sethuraman, Max Rucker, Onur Bagoren +3
In this paper, we present SonarSplat, a novel Gaussian splatting framework for imaging sonar that demonstrates realistic novel view synthesis and models acoustic streaking phenomen…
RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenes
Pou-Chun Kung, Skanda Harisha, Ram Vasudevan +2
High-Fidelity 3D scene reconstruction plays a crucial role in autonomous driving by enabling novel data generation from existing datasets. This allows simulating safety-critical sc…