In-Hwan Jin — accepted AI-conference papers

2026

MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting

In-Hwan Jin, Hyeongju Mun, Joonsoo Kim, Kugjin Yun, Kyeongbo Kong

ICLR 2026poster

Recent advances in dynamic scene reconstruction have significantly benefited from 3D Gaussian Splatting, yet existing methods show inconsistent performance across diverse scenes, indicating no single approach effectively handles all dynamic challenges. To overcome these limitations, we propose Mixtu…

Cited by 0 Source ↗Scholar ↗

2025

Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images

In-Hwan Jin, Haesoo Choo, Seong-Hun Jeong, Park Heemoon, Junghwan Kim, Oh-joon Kwon +1

ICLR 2025poster

To achieve realistic immersion in landscape images, fluids such as water and clouds need to move within the image while revealing new scenes from various camera perspectives. Recently, a field called dynamic scene video has emerged, which combines single image animation with 3D photography. These me…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗