Bingcai Wei

BPUL transforms image dehazing by effectively quantifying uncertainty and leveraging prior knowledge, leading to substantial quality improvements in restoration tasks.

PointVG-R achieves a groundbreaking 15.86-point boost in mIoU by integrating geometric reasoning into visual grounding tasks, reshaping our approach to spatial interpretation in models.

DRIVE-CHOREO achieves unprecedented multi-view consistency and BEV mAP by choreographing latent tokens across diverse modalities in autonomous driving.

Unified benchmarks reveal the state-of-the-art in simultaneously addressing multiple real-world image degradations like blur, low-light, and rain.