Reproduce “CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction” 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
Moyang Li, Zihan Zhu, Wei Zhang, Marc Pollefeys, Daniel Barath
CLoSeR adds loop closure to LoGeR by matching current and revisited image windows, predicting their relative poses, and optimizing frame poses on SE(3). The method relies on LoGeR’s scale consistency to avoid per-window scale estimation. On seven looping VBR Rome sequences, ATE RMSE is 11.15 m versus 36.16 m for LoGeR after Sim(3) alignment; loop closure cannot repair frontend failure.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.