|
In-Hwan Jin I'm an M.S. student in the Department of Electrical and Electronic Engineering at Pusan National University, where I work in the Computer Vision and Signal Processing (CVSP) Laboratory advised by Professor Kyeongbo Kong. My long-term goal is to develop Spatial Physical Intelligence, enabling AI to understand the physical world and predict its responses to actions. So far, I have worked on 3D/4D scene reconstruction and generation with Gaussian Splatting, from heterogeneous motion reconstruction to interactive environment generation. Building on this, I aim to develop physically grounded 3D/4D representations that integrate physical properties with geometry and motion. I am expected to graduate with my M.S. in August 2027 and am currently seeking Ph.D. positions. |
PublicationsFor a complete list of publications, please refer to my Google Scholar. * indicates equal contribution; † indicates corresponding author. |
|
Counterfactual Simulation-Guided Physical Reasoning for Physics-Based Video Generation Sohyeong Kim*, Woohyeong Kim*, In-Hwan Jin*, Hyeongju Mun, Kyeongbo Kong† Workshop on 3D in the Era of World Models (ECCV), 2026 paper / project page |
|
|
LivingWorld: Interactive 4D World Generation with Environmental Dynamics Hyeongju Mun*, In-Hwan Jin*, Sohyeong Kim, Kyeongbo Kong† ECCV, 2026 paper / project page / code |
|
|
On the Design of Mixture-of-Experts for Dynamic Gaussian Splatting In-Hwan Jin*, Hyeongju Mun*, Joonsoo Kim, Kugjin Yun, Kyeongbo Kong† IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026 paper / project page / code |
|
MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting In-Hwan Jin*, Hyeongju Mun*, Joonsoo Kim, Kugjin Yun, Kyeongbo Kong† ICLR, 2026 paper / project page / code |
|
FluIDWorld: Fluid-like Interactive Dynamics for 4D Worlds Hyeongju Mun*, In-Hwan Jin*, Sohyeong Kim, Kyeongbo Kong† Workshop on World Models: Understanding, Modelling and Scaling (ICLR), 2026 paper |
|
Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing Seong-Hun Jeong*, In-Hwan Jin*, Haesoo Choo*, Hyunjun Na*, Kyeongbo Kong† ACM TOMM, 2026 paper / project page / code |
|
|
Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images In-Hwan Jin*, Haesoo Choo*, Seong-Hun Jeong, Heemoon Park, Junghwan Kim, Oh-joon Kwon, Kyeongbo Kong† ICLR, 2025 paper / project page / code |
|
|
Dynamic Scene Reconstruction from Single Landscape Image Using 4D Gaussian in the Wild In-Hwan Jin*, Haesoo Choo, Seong-Hun Jeong, Heemoon Park, Oh-joon Kwon, Kyeongbo Kong† Workshop on 3D Modeling, Reconstruction, and Generation in the Wild (Wild3D, ECCV), 2024 paper / project page |
|
Enhancing Text-to-Video Editing with Motion Map Injection Seong-Hun Jeong*, In-Hwan Jin*, Haesoo Choo*, Hyunjun Na*, Kyeongbo Kong† Workshop on AI for Creative Video Editing and Understanding (ICCV), 2023 (Oral Presentation Invitation) |
Projects | |
|
Electronics and Telecommunications Research Institute (ETRI) 4D Gaussian representation learning and viewpoint augmentation software for high-quality virtual viewpoint synthesis, ETRI, Korea (Mar. 2026 – present) High-quality 4D space reconstruction software from multi-view images for light-field video data generation, ETRI, Korea (Mar. 2025 – Nov. 2025) 4D spatial representation generation and light-field video rendering software, ETRI, Korea (Aug. 2024 – Nov. 2024) |
|
Busan MBC Development of an immersive marine content production system using generative AI, Busan MBC, Korea (Jul. 2023 – Nov. 2024) |
Education Programs | |
|
University of Toronto AI Convergence Education Program, Jan. – Jun. 2027 |
|
POSCO AI/Big Data Academy (27th cohort), Jul. – Sep. 2024 |
Patents
|
Academic ServiceReviewer for ICLR (2027) and NeurIPS (2026) |
|
Website template from Jon Barron. |
