Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Good Noise Makes Good Edits: A Training-Free Diffusion-Based Video Editing with Image and Text Prompts
Saemee Choi, Sohyun Jeong, Hyojin Jang +2
We propose VINO, the first zero-shot, training-free video editing method conditioned on both image and text. Our approach introduces -start sampling and dilated dual masking to…
cs.CV2024
Training Spatial-Frequency Visual Prompts and Probabilistic Clusters for Accurate Black-Box Transfer Learning
Wonwoo Cho, Kangyeol Kim, Saemee Choi +1
Despite the growing prevalence of black-box pre-trained models (PTMs) such as prediction API services, there remains a significant challenge in directly applying general models to…