Introduces Fisher Information-guided stereo augmentation and uncertainty-aware regularization to mitigate overfitting in sparse-view 3D Gaussian Splatting.
Unifying approaches in active learning and active sampling via fisher information and information-theoretic quantities
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
ATLAS uses active learning with disentangled RNN ensembles to design experiments that recover RL agent models from bandit behavior 5-10x more efficiently than random or expert baselines in simulations.
MASS-DPO derives a Plackett-Luce-specific log-determinant Fisher information objective to select non-redundant negative samples, matching or exceeding multi-negative DPO performance with substantially fewer negatives across four benchmarks and three model families.
GAVIS quantifies per-particle anisotropic visibility in 3DGS via spherical harmonics, integrates it into a Bayesian rasterizer for real-time uncertainty, and uses maximum information gain for active mapping.
citing papers explorer
-
From Uncertainty to Stability and Fidelity: Guiding Sparse-View 3D Gaussian Splatting with Fisher Information
Introduces Fisher Information-guided stereo augmentation and uncertainty-aware regularization to mitigate overfitting in sparse-view 3D Gaussian Splatting.
-
ATLAS: Active Theory Learning for Automated Science
ATLAS uses active learning with disentangled RNN ensembles to design experiments that recover RL agent models from bandit behavior 5-10x more efficiently than random or expert baselines in simulations.
-
MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization
MASS-DPO derives a Plackett-Luce-specific log-determinant Fisher information objective to select non-redundant negative samples, matching or exceeding multi-negative DPO performance with substantially fewer negatives across four benchmarks and three model families.
-
Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
GAVIS quantifies per-particle anisotropic visibility in 3DGS via spherical harmonics, integrates it into a Bayesian rasterizer for real-time uncertainty, and uses maximum information gain for active mapping.