Bohao Zhang

Achieving superior depth estimation accuracy with 88.9% fewer parameters, X-Lens redefines efficiency in heterogeneous camera systems.

Humanoid-OmniOcc reveals that a stereo-based dataset can dramatically enhance occupancy prediction accuracy for humanoid robots, outperforming traditional monocular methods.

Motion cues and semantic alignment can significantly boost dynamic scene graph generation, especially for modeling nuanced relationships between objects in videos.