GaussLite conditions 3D Gaussian Splatting seeding density, gradient flow, and scaling on task relevance masks derived from LLM-parsed natural language and open-vocabulary detection, yielding +2.72 dB ROI PSNR gains on Replica and +2.23 dB on real hardware at fixed budget.
Bayesian fields: Task-driven open-set semantic gaussian splatting,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A map update operator with calibrated commit gates and conflict-drop windows improves committed map accuracy when integrating geometric perception and foundation-model semantics on KITTI-360 and ScanNet.
citing papers explorer
-
GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping
GaussLite conditions 3D Gaussian Splatting seeding density, gradient flow, and scaling on task relevance masks derived from LLM-parsed natural language and open-vocabulary detection, yielding +2.72 dB ROI PSNR gains on Replica and +2.23 dB on real hardware at fixed budget.
-
Belief Consistency Between Foundation-Model Evidence and Geometric Perception in Persistent Robotic Maps
A map update operator with calibrated commit gates and conflict-drop windows improves committed map accuracy when integrating geometric perception and foundation-model semantics on KITTI-360 and ScanNet.