Xiaofeng Wang

16

Papers

196

Total Citations

Papers (16)

DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation

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

EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation

NeurIPS 2025arXiv

ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation

Do Large Language Models Truly Understand Geometric Structures?

Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection

DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding

OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation

MVSTER: Epipolar Transformer for Efficient Multi-View Stereo

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

WonderTurbo: Generating Interactive 3D World in 0.72 Seconds

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition

Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark

CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification