Jaerin Lee — accepted AI-conference papers

2025

SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models

Jaerin Lee, Daniel Sungho Jung, Kanggeon Lee, Kyoung Mu Lee

CVPR 2025poster

We introduce SemanticDraw, a new paradigm of interactive content creation where high-quality images are generated in near real-time from given multiple hand-drawn regions, each encoding prescribed semantic meaning. In order to maximize the productivity of content creators and to fully realize their…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2022

Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring

Seungjun Nah, Sanghyun Son, Jaerin Lee, Kyoung Mu Lee

ICLR 2022poster

The goal of dynamic scene deblurring is to remove the motion blur in a given image. Typical learning-based approaches implement their solutions by minimizing the L1 or L2 distance between the output and the reference sharp image. Recent attempts adopt visual recognition features in training to impro…

Cited by 21 Source ↗PDF ↗Scholar ↗