Lune

CVPR2023

3D-Aware Multi-Class Image-to-Image Translation with NeRFs

Senmao Li, Joost van de Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang

DOIPublisher

Abstract

Figure 1 . 3D-aware I2I translation: given a view-consistent 3D scene (the input), our method maps it into a high-quality target-specific image. Our approach produces consistent results across viewpoints.