Kun Zhan

13

Papers

121

Total Citations

Papers (13)

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

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion

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

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

Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction

RoboPearls: Editable Video Simulation for Robot Manipulation

StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models

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

BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities

Hierarchical Consensus Network for Multiview Feature Learning

DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation