Multi-style Neural Radiance Field with AdaIN
This work addresses the need for more flexible and controllable stylization in 3D scene rendering, though it appears incremental as it builds on existing NeRF and AdaIN methods.
The authors tackled the problem of stylized novel view synthesis by proposing a pipeline that combines AdaIN and NeRF, resulting in a model that handles multiple styles, performs well on styles with strong brush strokes, and allows style interpolation for better control.
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.