GauSS-MI estimates the expected visual information gain of a viewpoint from per-Gaussian reliability probabilities, and an active reconstruction system using it achieves high visual fidelity with fewer frames.
Information-theoretic planning with tra- jectory optimization for dense 3d mapping
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction
GauSS-MI estimates the expected visual information gain of a viewpoint from per-Gaussian reliability probabilities, and an active reconstruction system using it achieves high visual fidelity with fewer frames.