1 citations · 1 across the 3 of their papers we have counts for
4 papers
Prior-Driven Enhancements in 3D Gaussian Splatting: Normals and Depths Regularization
Gyeonggwan Lee, Seunghwan Hong, Junghun Suh
3D Gaussian Splatting (3DGS) is a state-of-the-art technique for 3D scene rendering, offering high efficiency and excellent visual quality. However, because 3DGS relies on an initi…
SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence
Gyeonggwan Lee, Eunsoo Im, Seunghwan Hong +1
Dense feature matching between 360 panoramas underpins omnidirectional pose estimation, 3D reconstruction, and SLAM. Such panoramas are stored in the equirectangular projec…
CVSD-Reg: Cross-Modal Visual Semantic Prior Distillation for Robust LiDAR Registration
Eunsoo Im, Junghun Suh, Gyeonggwan Lee +1
Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in poi…
PRISM-SLAM: Probabilistic Ray-Grounded Inference for Scale-aware Metric SLAM
Eunsoo Im, Gyeonggwan Lee, Seunghwan Hong +1
Monocular SLAM historically suffers from scale ambiguity and tracking failure in dynamic environments. While recent vision foundation models (VFMs) provide remarkable zero-shot dep…