Zhixin Cheng

RayI2P: Learning Rays for Image-to-Point Cloud Registration

VCR: Variance-aware Channel Recalibration Network for Low Light Image with Distribution Alignment

Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models

Learning Overlap Detection for Domain-Adaptive Image-to-Point Cloud Registration

Learning to Enhance Low-Light Images with Reliable Attention and Reinforced Distribution Alignment

EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting

BeyondMix: Leveraging Structural Priors and Long-Range Dependencies for Domain-Invariant LiDAR Segmentation