4 papers
FEAT: Fashion Editing and Try-On from Any Design
Soye Kwon, Keonyoung Lee, Dahuin Jung +1
Fashion design aims to express a designer's creative intent and to depict how garments interact with the human body. Recent methods condition on multimodal inputs to support garmen…
Multi-aspect Knowledge Distillation with Large Language Model
Taegyeong Lee, Jinsik Bang, Soyeong Kwon +1
Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or…
Grid Diffusion Models for Text-to-Video Generation
Taegyeong Lee, Soyeong Kwon, Taehwan Kim
Recent advances in the diffusion models have significantly improved text-to-image generation. However, generating videos from text is a more challenging task than generating images…
Zero-shot Text-guided Infinite Image Synthesis with LLM guidance
Soyeong Kwon, Taegyeong Lee, Taehwan Kim
Text-guided image editing and generation methods have diverse real-world applications. However, text-guided infinite image synthesis faces several challenges. First, there is a lac…