Event6D: Event-based Novel Object 6D Pose Tracking
Event6D is an event-based framework for real-time novel object 6D pose tracking that reconstructs intensity and depth from event streams and introduces a benchmark with synthetic …
Jae-Young Kang*
•
•
1 min read
DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR
DSERT-RoLL is a multimodal driving dataset featuring stereo event, RGB, and thermal cameras together with 4D radar and dual LiDAR, providing unified 2D and 3D detection benchmarks …
Hoonhee Cho*
VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting
An end-to-end autonomous driving framework that achieves viewpoint robustness by jointly learning feed-forward 3D Gaussian splatting for planning-aware view synthesis.
Hoonhee Cho*
Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection
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 …
Jae-Young Kang*
Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras
Event-based 3D object detection leveraging asynchronous event cameras to overcome blind times in autonomous driving.
Hoonhee Cho*
Unifying Low-Resolution and High-Resolution Alignment by Event Cameras for Space-Time Video Super-Resolution
Space-time video super-resolution using event cameras to jointly align low- and high-resolution information.
Hoonhee Cho
Temporal Event Stereo via Joint Learning with Stereoscopic Flow
Event-based stereo matching method that jointly learns temporal and stereoscopic flow.
Hoonhee Cho*