From the 1 of 6 linked papers with an AI index.
6 papers
Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment
Boyuan Wang, Zhenyuan Zhang, Zhiqin Yang +16
Zero2Skill is a robot learning system that autonomously collects, verifies, and resets manipulation data while using a large language model to store and reuse human corrections, dr…
Empowering Feed-Forward Reconstruction Models with Metric Scale via Satellite Images
Xianghui Ze, Yongjian Luo, Mengjun Chao +3
Feed-forward 3D reconstruction models have recently shown strong generalization across diverse scenes, yet most of them recover geometry only up to an unknown global scale. This sc…
Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images
Qiwei Wang, Zhongyao Tuo, Xianghui Ze +1
Cross-view localization classically asks: where does this ground image lie on the satellite tile? Existing methods are typically limited to 3-DoF estimates -- an position a…
CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis
Qiwei Wang, Xianghui Ze, Jingyi Yu +1
Feed-forward 3D Gaussian Splatting (3DGS) has shown great promise for real-time novel view synthesis, but its application to panoramic imagery remains challenging. Existing methods…
SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery
Xianghui Ze, Beiyi Zhu, Zhenbo Song +2
Generating multiview-consistent ground-level scenes from satellite imagery is a challenging task with broad applications in simulation, autonomous navigation, and digit…
Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
Xianghui Ze, Zhenbo Song, Qiwei Wang +2
Generating street-view images from satellite imagery is a challenging task, particularly in maintaining accurate pose alignment and incorporating diverse environmental conditions.…