5 papers
ZYT-World: A Real-Time Controllable World Model for Closed-Loop Autonomous-Driving Simulation
Boni Hu, Xiong Wei, Haoming Huang +20
Generative world models offer controllable and repeatable closed-loop simulation for end-to-end and vision-language-action driving policies, but production deployment exposes three…
SpotlessGS: Relightable 3D Gaussian Splatting under Dynamic Illumination for Robotic Perception
Liang Hong, Jiaxin Wei, Simon Schaefer +2
Robots operating in dark or poorly lit environments rely on onboard lights, which often produce uneven illumination that degrades downstream perception tasks. Prior approaches base…
Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
Hanlin Chen, Jiaxin Wei, Xibin Song +5
Frame-wise action-controlled image-to-video generation is a promising paradigm for interactive world simulation, where each control signal should elicit an immediate visual respons…
GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting
Jiaxin Wei, Stefan Leutenegger, Simon Schaefer
Recent developments in 3D Gaussian Splatting have significantly enhanced novel view synthesis, yet generating high-quality renderings from extreme novel viewpoints or partially obs…
GSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF Fusion
Jiaxin Wei, Stefan Leutenegger
Traditional volumetric fusion algorithms preserve the spatial structure of 3D scenes, which is beneficial for many tasks in computer vision and robotics. However, they often lack r…