CVPR Daily - Thursday

Reflecting on being recognized among the top 20 papers at CVPR , we want to know if Nico, Mathias, and Carter have contemplated the reasons behind the judge’s decision. How has the paper transcended being a mere poster or highlight material to deserve an award? “ Event-based feature tracking was often regarded as very promising for the application of event cameras , but it’s never been robustly shown to work to such a degree that people think you could apply it directly and gain huge benefits,” Mathias points out. “One issue was that modeling event cameras is very difficult. Even for our lab, which is quite expert in this, it’s not straightforward. In our solution, we overcome the longstanding challenge of event- based feature tracking in a data- driven fashion, letting the benefits of event cameras shine. This is reflected also in the experimental results, where we show over 100% gain over the baseline . It’s not very common in computer vision to have such strong results. ” 7 DAILY CVPR Thursday Data-driven Feature Tracking for Event Cameras