Multi-style Neural Radiance Field with AdaIN

TL;DR

This paper introduces a simplified, multi-style Neural Radiance Field (NeRF) model using AdaIN that enables flexible style transfer, interpolation, and strong brush stroke stylization for novel view synthesis.

Contribution

It presents a unified pipeline combining AdaIN with NeRF, extending multi-style capabilities and style interpolation with improved architecture for expressive stylizations.

Findings

Supports multiple styles with a single model

Enables style interpolation and intensity control

Performs well with styles featuring strong brush strokes

Abstract

In this work, we propose a novel pipeline that combines AdaIN and NeRF for the task of stylized Novel View Synthesis. Compared to previous works, we make the following contributions: 1) We simplify the pipeline. 2) We extend the capabilities of model to handle the multi-style task. 3) We modify the model architecture to perform well on styles with strong brush strokes. 4) We implement style interpolation on the multi-style model, allowing us to control the style between any two styles and the style intensity between the stylized output and the original scene, providing better control over the stylization strength.