Dahyeon Kye
Hi, I'm Dahyeon Kye, a PhD student in the CMLab, advised
by Prof. Jihyong Oh.
My research focuses on generative models for visual content, spanning image and video generation, editing, and restoration. I am also interested in 3D/4D generation, world simulation, and interactive generative models that allow users to interact with and shape dynamic visual worlds.
News
- 2026.03 AceVFI accepted at IEEE TCSVT!
Under Review / Preprints
🦁 CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metric
Dahyeon Kye*, Jeahun Sung*, Minkyu Jeon, Jihyong Oh†
✨Collaborator Princeton University
Project page · arXiv · Code · Paper
-
Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models
Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae, Jihyong Oh
✨Collaborator Kyung Hee University
Project page · arXiv · Code
-
RefGC-SR²: Reference-guided Generated Content Super-Resolution and RefinementJeahun Sung*, Dahyeon Kye*, Soo Ye Kim†, Jihyong Oh†
✨Collaborator Adobe Research
Project page · arXiv · Code
Accepted / Publications
-
CVPR 2026 (Findings)✨ FLAIR: Frequency- and Locality-Aware Implicit Neural Representations
Sukhun Ko, Seokhyun Youn, Dahyeon Kye, Kyle Min, Chanho Eom, Jihyong Oh†
✨Collaborator Oracle
Project page · Paper · arXiv · Code · YouTube
-
IEEE TCSVT 2026
AceVFI: A Comprehensive Survey of Advances in Video Frame InterpolationDahyeon Kye, Changhyun Roh, Sukhun Ko, Chanho Eom, Jihyong Oh†
Paper · arXiv · Awesome page
* equal contribution · † corresponding author · full list: Scholar / CMLab