5 papers
InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image
Gwanhyeong Koo, Hyunsu Kim, Youngji Kim +5
Recent advances in single image-to-3D generation have enabled high-quality asset synthesis, yet extending these capabilities to indoor scene generation remains challenging. Existin…
GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport
Youngju Na, Jaeseong Yun, Soohyun Ryu +3
While 3D Gaussian splatting has emerged as a powerful paradigm, it fundamentally fails to model transparency such as glass panels. The core challenge lies in decoupling the intertw…
Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning
Dongki Jung, Jaehoon Choi, Adil Qureshi +3
We present Wid3R, a feed-forward neural network for multi-view visual geometry reconstruction that supports wide field-of-view camera models. Unlike existing methods that assume re…
EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching
Dongki Jung, Jaehoon Choi, Yonghan Lee +4
We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidi…
Mode-GS: Monocular Depth Guided Anchored 3D Gaussian Splatting for Robust Ground-View Scene Rendering
Yonghan Lee, Jaehoon Choi, Dongki Jung +4
We present a novel-view rendering algorithm, Mode-GS, for ground-robot trajectory datasets. Our approach is based on using anchored Gaussian splats, which are designed to overcome…