Reproduce “Temporal Residual Bottleneck for Robust Asynchronous Collaborative Perception” 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
Melih Yazgan, Ahmed Abouelazm, J. Marius Zöllner
The method improves delayed collaborative vehicle detection by retaining a pose-corrected collaborator map as the baseline and applying a gated correction suggested by recent cached history. On DAIR-V2X at irregular 500 ms delay, [email protected] drops from 0.664 to 0.635, versus LRCP’s 0.669 to 0.611. This halves degradation, but gives up synchronized accuracy and is not a win in every condition.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.