8 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…
SARA: Scene-Aware Reconstruction Accelerator
Jee Won Lee, Hansol Lim, Minhyeok Im +2
We present SARA (Scene-Aware Reconstruction Accelerator), a geometry-driven pair selection module for Structure-from-Motion (SfM). Unlike conventional pipelines that select pairs b…
LiteVoxel: Low-memory Intelligent Thresholding for Efficient Voxel Rasterization
Jee Won Lee, Jongseong Brad Choi
Sparse-voxel rasterization is a fast, differentiable alternative for optimization-based scene reconstruction, but it tends to underfit low-frequency content, depends on brittle pru…
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…
A Hybrid Surrogate for Electric Vehicle Parameter Estimation and Power Consumption via Physics-Informed Neural Operators
Hansol Lim, Jongseong Brad Choi, Jee Won Lee +2
We present a hybrid surrogate model for electric vehicle parameter estimation and power consumption. We combine our novel architecture Spectral Parameter Operator built on a Fourie…
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,…