Uni-SLAM combines a model-free predictive uncertainty, based on volume rendering termination probability, with decoupled hash grids and strategic bundle adjustment to achieve state-of-the-art dense RGB-D SLAM on Replica, ScanNet, and TUM RGB-D.
Pixel-wise prediction based visual odometry via uncertainty estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction
Uni-SLAM combines a model-free predictive uncertainty, based on volume rendering termination probability, with decoupled hash grids and strategic bundle adjustment to achieve state-of-the-art dense RGB-D SLAM on Replica, ScanNet, and TUM RGB-D.