Multi-modal driving dataset with stereo event, RGB, and thermal cameras, 4D radar, and dual LiDAR, supporting diverse weather and illumination conditions with 2D/3D annotations and …
Event-based 6D object tracking for high-speed, dynamic scenarios.
Event-based motion deblurring framework that operates entirely in an unpaired setting, leveraging event cameras to bridge blur and sharp domains without aligned supervision.
Event-Image Fusion stereo matching method that jointly learns temporal and stereoscopic flow.
A continuous-time 3D object detection framework that relies solely on stereo event cameras, exploiting their high temporal resolution with dual filters and object-centric …
An unsupervised domain adaptation framework for 2D human pose estimation under extreme motion blur, leveraging event cameras and event-based augmentation without target-domain …
Event-based 3D object detection leveraging asynchronous event cameras to overcome blind times in autonomous driving.
Space-time video super-resolution using event cameras to jointly align low- and high-resolution information.
A large-scale benchmark dataset for event-guided human pose estimation and tracking under extreme conditions.
Unpaired day-to-night event translation for robust nighttime event-based perception.