4 papers
SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation
Dijie Zhu, Seunghun Oh, Ruopeng Huang +3
Reliable performance evaluation is a central bottleneck for deploying robot-learning policies in real-world conditions. Real-world testing is faithful but costly and difficult to s…
Steady-Forcing: Balancing Spatial Persistence and Motion Continuity in Long-Horizon Nature Video Diffusion
Matiur Rahman Minar, Seunghun Oh, GangHyeon Jeong +1
Autoregressive video diffusion models enable streaming generation but often degrade over long rollouts: static scene layouts drift, while mechanisms that improve spatial stability…
SVRecon: Sparse Voxel Rasterization for Surface Reconstruction
Seunghun Oh, Jaesung Choe, Dongjae Lee +4
We extend the recently proposed sparse voxel rasterization paradigm to the task of high-fidelity surface reconstruction by integrating Signed Distance Function (SDF), named SVRecon…
The City that Never Settles: Simulation-based LiDAR Dataset for Long-Term Place Recognition Under Extreme Structural Changes
Hyunho Song, Dongjae Lee, Seunghun Oh +2
Large-scale construction and demolition significantly challenge long-term place recognition (PR) by drastically reshaping urban and suburban environments. Existing datasets predomi…