CVPR Daily - Thursday

8 DAILY CVPR Thursday Nico says the future application of the method has likely played a role in the paper’s success. It demonstrates the possibility of combining traditional image approaches with events, reducing bandwidth in certain applications. While not explicitly shown in the paper, this reduced bandwidth is significant for virtual and augmented reality scenarios . Tracking images with events makes it possible to make real-time decisions about feature track quality and request new images when necessary. This approach can result in lower frame rates, bandwidth requirements, and power consumption. “ Event cameras have been promising, especially for applications like feature tracking, where the benefits of high speed and high dynamic range have been promised , and our work unlocks that in a data-driven fashion, ” Carter ponders. “ At a higher level, our proposed algorithm is quite simple! It’s a straightforward idea that works well, so that’s also something in our favor. ” Thinking about the next steps for this work, the team plan to revisit the initial motivation to use the feature tracker for pose estimation. They want to integrate it with a VO pipeline to improve the overall estimation of the camera pose. Additionally, an open question remains regarding which features to track. “ In this paper, we predetermined which features we wanted to track, ” Mathias reveals. “ You can imagine that certain features are easier to track in certain scenarios than others, but at the moment, this is completely handcrafted. Eventually, the process could be optimized end to end with a visual odometry or visual-inertial odometry pipeline . ” To learn more about this work, visit Poster 144 today [Thursday] afternoon from 16:30-18:30 in the West Exhibit Hall. It was chosen as an award candidate - check it out! Best Paper Award Candidate