4 papers
TIDI-GS: Floater Suppression in 3D Gaussian Splatting for Enhanced Indoor Scene Fidelity
Sooyeun Yang, Cheyul Im, Jee Won Lee +1
3D Gaussian Splatting (3DGS) is a technique to create high-quality, real-time 3D scenes from images. This method often produces visual artifacts known as floaters--nearly transpare…
Hybrid Vision Servoing with Depp Alignment and GRU-Based Occlusion Recovery
Jee Won Lee, Hansol Lim, Sooyeun Yang +1
Vision-based control systems, such as image-based visual servoing (IBVS), have been extensively explored for precise robot manipulation. A persistent challenge, however, is maintai…
Micro-splatting: Multistage Isotropy-informed Covariance Regularization Optimization for High-Fidelity 3D Gaussian Splatting
Jee Won Lee, Hansol Lim, Sooyeun Yang +1
High-fidelity 3D Gaussian Splatting methods excel at capturing fine textures but often overlook model compactness, resulting in massive splat counts, bloated memory, long training,…
MATT-GS: Masked Attention-based 3DGS for Robot Perception and Object Detection
Jee Won Lee, Hansol Lim, SooYeun Yang +1
This paper presents a novel masked attention-based 3D Gaussian Splatting (3DGS) approach to enhance robotic perception and object detection in industrial and smart factory environm…