Xingang Wang

19

Papers

275

Total Citations

Papers (19)

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

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

DiffBEV: Conditional Diffusion Model for Bird’s Eye View Perception

Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation

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

NeurIPS 2025arXiv

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

Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection

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

Multi-Granularity Distillation Scheme towards Lightweight Semi-Supervised Semantic Segmentation

MVSTER: Epipolar Transformer for Efficient Multi-View Stereo

HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation

DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup

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

Attention-Guided Unified Network for Panoptic Segmentation

Learning Dynamic Routing for Semantic Segmentation

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

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception