👋 Hello World! I am Kwanggyoon Edward Seo currently a PhD candiate at VML KAIST.
My research lies at the intersection of deep learning, computer vision, and computer graphics. Specifically, I am interests in generative AI focusing on synthesizing and manipulating images, video, and 3D human.
personal page / google scholar / email
- PhD @ GSCT, KAIST - 2018~2024 (expected)
- MS @ GSCT, KAIST - 2016~2018
- BS @ EE, KAIST - 2011~2016
- Research assistant @ KAIST VML - Jan. 2017 ~ Present
- Research intern @ Adobe Research - Jun. 2022 ~ Aug. 2022
- Research intern @ Adobe Research - Mar. 2021 ~ Jun. 2021
- Research intern @ Naver Clova - Dec. 2019 ~ Jun. 2020
- Software Intern @ Golfzon - Dec. 2015 ~ Feb. 2016
- Emotion Manipulation for Talking-head Videos - in submission
- Audio-Driven Emotional Talking-Head Generation - in submission
- Landscape Cinemagraph Generation - CVPR 2024
- Stylized Sketch Extraction via Generative Prior with Limited Data - EG 2024
- StylePortraitVideo: Editing Portrait Videos with Expression Optimization - PG 2022
- Deep Learning-based Unsupervised Human Facial Retargeting - PG 2021
- Virtual Camera Layout Generation using a Reference Video - CHI 2021
- Neural Crossbreed: Neural Based Image Metamorphosis - SIGGRAPH Asia 2020