Reproduce “ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras” 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
Junkai Niu, Sheng Zhong, Xiuyuan Lu, Shaojie Shen, Guillermo Gallego, Yi Zhou
ESVO2 estimates camera motion and a local 3D map from stereo event data, using adaptive event-contour sampling, static and temporal stereo, and IMU pre-integration. Its back-end updates inertial biases and velocity. On DSEC city04 a, it reports 56.17 cm RMS absolute trajectory error, versus 370.32 cm for ESVO; this single-sequence result does not establish superiority across all scenes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.