Minjung Shin — accepted AI-conference papers

2026

MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion

Minjung Shin, Hyunin Cho, Sooyeon Go, Jin-Hwa Kim, Youngjung Uh

ICLR 2026poster

Multi-view generation with camera pose control and prompt-based customization are both essential elements for achieving controllable generative models. However, existing multi-view generation models do not support customization with geometric consistency, whereas customization models lack explicit…

Cited by 0 Source ↗Scholar ↗

2023

BallGAN: 3D-aware Image Synthesis with a Spherical Background

Minjung Shin, Yunji Seo, Jeongmin Bae, Young Sun Choi, Hyunsu Kim, Hyeran Byun +1

ICCV 2023poster

3D-aware GANs aim to synthesize realistic 3D scenes that can be rendered in arbitrary camera viewpoints, generating high-quality images with well-defined geometry. As 3D content creation becomes more popular, the ability to generate foreground objects separately from the background has become a cruc…

Cited by 7 PDF ↗Scholar ↗