Seung-Wook Kim

Asymmetric blur artifacts in stereo images can be effectively mitigated using a lightweight attention mechanism that respects physical constraints, leading to significant improvements in image restoration.

Achieving stable and consistent scene-level geometry transformation in 3D style transfer could redefine how we approach visual realism in computer graphics.

CCDM offers a groundbreaking way to predict synthetic dataset effectiveness, achieving perfect correlation with model performance without the need for training.