6 papers
Robust Structureless Monocular Visual Inertial Initialization Exploiting Line Features and Vanishing Points
Junwan Choi, Woongrae Jo, Dong-Uk Seo +2
Accurate initialization is essential for reliable visual-inertial odometry (VIO), but it is often ill-conditioned under degenerate motions. Existing methods typically require restr…
PLED-VINS: A Point-Line Event-Based Visual Inertial SLAM for Dynamic Environments
Seunghun Lee, Jihun Nam, Dong-Uk Seo +1
Dynamic environments remain a fundamental challenge for visual SLAM, where unreliable observations from moving objects and rapid motion degrade state estimation accuracy. Although…
GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow
Dong-Uk Seo, Jinwoo Jeon, Eungchang Mason Lee +1
Gaussian splatting has recently gained traction as a compelling map representation for SLAM systems, enabling dense and photo-realistic scene modeling. However, its application to…
AIM-SLAM: Dense Monocular SLAM via Adaptive and Informative Multi-View Keyframe Prioritization with Foundation Model
Jinwoo Jeon, Dong-Uk Seo, Eungchang Mason Lee +1
Recent advances in geometric foundation models have emerged as a promising alternative for addressing the challenge of dense reconstruction in monocular visual simultaneous localiz…
PaGO-LOAM: Robust Ground-Optimized LiDAR Odometry
Dong-Uk Seo, Hyungtae Lim, Seungjae Lee +1
Numerous researchers have conducted studies to achieve fast and robust ground-optimized LiDAR odometry methods for terrestrial mobile platforms. In particular, ground-optimized LiD…
Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM
Jinwoo Jeon, Hyunjun Lim, Dong-Uk Seo +1
Feature-based visual simultaneous localization and mapping (SLAM) methods only estimate the depth of extracted features, generating a sparse depth map. To solve this sparsity probl…