Reproduce “Gassidy: Gaussian Splatting SLAM in Dynamic Environments” 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
Long Wen, Shixin Li, Yu Zhang, Yuhong Huang, Jianjie Lin, Fengjunjie Pan, Zhenshan Bing, Alois Knoll
Gassidy is a dense RGB-D SLAM system that maps changing scenes while estimating a robot’s camera path. It separates object instances from background using instance masks, then tracks rendering-error changes during alignment to exclude likely moving regions from tracking and mapping. On four dynamic TUM RGB-D sequences, it reports 97.9% lower mean ATE RMSE than SplaTAM, a static-scene 3DGS baseline.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.