Generative Computing Lab
인하대학교 생성컴퓨팅 연구실은 일반 사용자부터 분야별 전문가에 이르기까지, 누구나 생성형 AI의 혜택을 누릴 수 있도록 접근성과 사회적 효용을 극대화한 인간 중심의 기술을 연구합니다. 나아가 생성형 AI의 책임감 있는 발전을 위해 데이터 보안과 윤리적 가치를 보장하는 신뢰 시스템 구축에 주력하고 있습니다.
Research Highlights
GCL News
Jan 2026
One paper Compositional Image Synthesis with Inference-Time Scaling has been accepted to ICASSP 2026.
Nov 2025
One paper T2LF: LLM-Guided Multimodal Diffusion for Text-to-Light Field Synthesis has been accepted to WACV 2026.
Oct 2025
Professor Ahn has been invited to present a tutorial titled "Responsible Generative AI: From Provenance to Protection" at ICCE-Asia 2025.
Aug 2025
One paper DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Models has been accepted to Expert Systems with Applications (ESWA).
July 2025
One paper Imperceptible Protection Against Style Imitation from Diffusion Models has been accepted to IEEE Transactions on Multimedia (TMM).
Compositional Image Synthesis with Inference-Time Scaling (ICASSP 2026)
Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models (CVPR 2025)
DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models (AAAI 2024)
DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models (Expert Systems with Applications)
AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks (ICCV 2023)
Interactive Cartoonization with Controllable Perceptual Factors (CVPR 2023)
WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylization (SIGGRAPH Asia TC 2022)
Rethinking Data Augmentation for Image Super-Resolution: A Comprehensive Analysis and a New Strategy (CVPR 2020)