Class-Continuous Conditional Generative Neural Radiance Field

TL;DR

This paper introduces C3G-NeRF, a novel neural radiance field model capable of generating high-quality, 3D-consistent images with conditional and continuous feature manipulation, improving 3D-aware image synthesis.

Contribution

C3G-NeRF is the first model to enable class-continuous conditional manipulation in neural radiance fields for photorealistic 3D-consistent image synthesis.

Findings

Strong 3D consistency with fine details

Smooth interpolation in conditional features

Achieved FID of 7.64 on face image synthesis

Abstract

The 3D-aware image synthesis focuses on conserving spatial consistency besides generating high-resolution images with fine details. Recently, Neural Radiance Field (NeRF) has been introduced for synthesizing novel views with low computational cost and superior performance. While several works investigate a generative NeRF and show remarkable achievement, they cannot handle conditional and continuous feature manipulation in the generation procedure. In this work, we introduce a novel model, called Class-Continuous Conditional Generative NeRF ($\text{C}^{3}$G-NeRF), which can synthesize conditionally manipulated photorealistic 3D-consistent images by projecting conditional features to the generator and the discriminator. The proposed $\text{C}^{3}$G-NeRF is evaluated with three image datasets, AFHQ, CelebA, and Cars. As a result, our model shows strong 3D-consistency with fine details and smooth interpolation in conditional feature manipulation. For instance, $\text{C}^{3}$G-NeRF exhibits a Fr\'echet Inception Distance (FID) of 7.64 in 3D-aware face image synthesis with a $\text{128}^{2}$ resolution. Additionally, we provide FIDs of generated 3D-aware images of each class of the datasets as it is possible to synthesize class-conditional images with $\text{C}^{3}$G-NeRF.