From the 1 of 5 linked papers with an AI index.
5 papers
LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM
Sibaek Lee, Seongbo Ha, Kyeongsu Kang +3
LEGO-SLAM integrates compressed language embeddings into a 3D Gaussian Splatting SLAM system, enabling real-time open‑vocabulary mapping, semantic pruning, and loop detection.
TriLift: Interpolation-Free Tri-Plane Lifting for Efficient 3D Perception on Embedded Systems
Sibaek Lee, Jiung Yeon, Hyeonwoo Yu
Dense 3D convolutions provide high accuracy for perception but are too computationally expensive for real-time robotic systems. Existing tri-plane methods rely on 2D image features…
LAMP: Implicit Language Map for Robot Navigation
Sibaek Lee, Hyeonwoo Yu, Giseop Kim +1
Recent advances in vision-language models have made zero-shot navigation feasible, enabling robots to follow natural language instructions without requiring labeling. However, exis…
LangGS-SLAM: Real-Time Language-Feature Gaussian Splatting SLAM
Seongbo Ha, Sibaek Lee, Kyungsu Kang +3
In this paper, we propose a RGB-D SLAM system that reconstructs a language-aligned dense feature field while sustaining low-latency tracking and mapping. First, we introduce a Top-…
Bayesian NeRF: Quantifying Uncertainty with Volume Density for Neural Implicit Fields
Sibeak Lee, Kyeongsu Kang, Seongbo Ha +1
We present a Bayesian Neural Radiance Field (NeRF), which explicitly quantifies uncertainty in the volume density by modeling uncertainty in the occupancy, without the need for add…