Peng Jia

6

Papers

56

Total Citations

Papers (6)

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration

S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking

RoboPearls: Editable Video Simulation for Robot Manipulation

HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving