4 papers
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…
LF-GICP: Parameter-Free Degeneracy-Aware LiDAR Odometry via a Voxel-Normal Localizability Field
Eunsoo Im
Scan-to-map LiDAR odometry drifts unboundedly along the unobservable axes of geometrically degenerate environments like tunnels and corridors, and existing degeneracy handling requ…
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…
GATE3D: Generalized Attention-based Task-synergized Estimation in 3D*
Eunsoo Im, Changhyun Jee, Jung Kwon Lee
The emerging trend in computer vision emphasizes developing universal models capable of simultaneously addressing multiple diverse tasks. Such universality typically requires joint…