A Gaussian-splatting RGB-D SLAM pipeline reconstructs photorealistic dynamic scenes by modeling humans with SMPL and rigid items with optical-flow alignment, and reports lower camera trajectory error than three published baselines.
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments
A Gaussian-splatting RGB-D SLAM pipeline reconstructs photorealistic dynamic scenes by modeling humans with SMPL and rigid items with optical-flow alignment, and reports lower camera trajectory error than three published baselines.