“3D Art Research with Radiance Field and Style Transfer” takes NeRF as a backbone, exploring and experimenting with different methods to make 3D style transfer possible by combining the 2D style transfer technique with photo-realistic 3D scenes from NeRF together. Joshua Cao’s thesis validly compares different approaches that rarely appear in research papers.
The project explores the applications that can utilize such techniques to achieve architecture design and art creation through 3D-aware style control and transfer. To explore the topic, the generation of the datasets for the network is discussed, and different ways of combining NeRF network and Style transfer network are implemented and analyzed, including latent space embedding of various features and concatenation of two networks. Finally, experiments are conducted to use such networks to generate 3D art pieces.
This project was made possible by FRFF microgrant #2023-019.