Picture for Minho Park

Minho Park

Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models

Add code
Jun 08, 2024
Viaarxiv icon

StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

Add code
Dec 04, 2023
Figure 1 for StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On
Figure 2 for StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On
Figure 3 for StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On
Figure 4 for StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On
Viaarxiv icon

Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis

Add code
Aug 16, 2023
Viaarxiv icon

iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer

Add code
Jul 15, 2022
Figure 1 for iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer
Figure 2 for iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer
Figure 3 for iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer
Figure 4 for iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer
Viaarxiv icon

Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images

Add code
Apr 14, 2021
Figure 1 for Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images
Figure 2 for Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images
Figure 3 for Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images
Figure 4 for Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images
Viaarxiv icon

Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands

Add code
Jul 02, 2019
Figure 1 for Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands
Figure 2 for Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands
Figure 3 for Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands
Figure 4 for Generative Guiding Block: Synthesizing Realistic Looking Variants Capable of Even Large Change Demands
Viaarxiv icon