Class-Continuous Conditional Generative Neural Radiance Field
Jiwook Kim (Chung-Ang University),* Minhyeok Lee (Chung-Ang University)
The 34th British Machine Vision Conference
Abstract
The focus of 3D-aware image synthesis lies in preserving spatial consistency while generating high-resolution images with fine details. Recently, Neural Radiance Field (NeRF) has emerged as a powerful method for synthesizing novel views with low computational cost and exceptional performance. Although existing generative NeRF approaches have achieved significant results, they are unable to handle conditional and continuous feature manipulation during the generation process. In this work, we present a novel model, called Class-Continuous Conditional Generative NeRF (C³G-NeRF), which synthesizes conditionally manipulated photorealistic 3D-consistent images by projecting conditional features onto the generator and discriminator. We evaluate the proposed C³G-NeRF on three image datasets: AFHQ, CelebA, and Cars. Our model demonstrates robust 3D-consistency, fine details, ability of 360° generation, and smooth interpolation in conditional feature manipulation. For example, C³G-NeRF achieves a Fréchet Inception Distance (FID) of 7.64 in 3D-aware face image synthesis with a 128² resolution. Furthermore, we provide FIDs and for generated 3D-aware images of each class within the datasets, showcasing the ability of C³G-NeRF to synthesize class-conditional images.Video
Citation
@inproceedings{Kim_2023_BMVC,
author = {Jiwook Kim and Minhyeok Lee},
title = {Class-Continuous Conditional Generative Neural Radiance Field},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0243.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by