Reproduce “Edged USLAM: Edge-Aware Event-Based SLAM with Learning-Based Depth Priors” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Şebnem Sarıözkan, Hürkan Şahin, Olaya Álvarez-Tuñón, Erdal Kayacan
Edged USLAM extends a visual-inertial SLAM system by enhancing motion-compensated event images for feature tracking and adding a coarse depth prior, while retaining conventional frames and IMU. Across ten HKU and VECtor sequences, its average position RMSE was 0.35 m, versus DEVO’s 0.29 m. In indoor flight tests its average APE was 0.38 m, but results vary by condition.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.