G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Styles
This addresses the efficiency and applicability limitations for researchers and practitioners in 3D graphics and style transfer, though it appears incremental as it builds on existing NeRF and style transfer methods.
The paper tackles the problem of inefficient per-scene optimization in 3D style transfer with Neural Radiance Fields (NeRF) by proposing a generalizable model that renders stylized novel views without per-scene or per-style optimization, achieving comparable visual quality while significantly enhancing efficiency and applicability.
Neural Radiance Fields (NeRF) have emerged as a powerful tool for creating highly detailed and photorealistic scenes. Existing methods for NeRF-based 3D style transfer need extensive per-scene optimization for single or multiple styles, limiting the applicability and efficiency of 3D style transfer. In this work, we overcome the limitations of existing methods by rendering stylized novel views from a NeRF without the need for per-scene or per-style optimization. To this end, we take advantage of a generalizable NeRF model to facilitate style transfer in 3D, thereby enabling the use of a single learned model across various scenes. By incorporating a hypernetwork into a generalizable NeRF, our approach enables on-the-fly generation of stylized novel views. Moreover, we introduce a novel flow-based multi-view consistency loss to preserve consistency across multiple views. We evaluate our method across various scenes and artistic styles and show its performance in generating high-quality and multi-view consistent stylized images without the need for a scene-specific implicit model. Our findings demonstrate that this approach not only achieves a good visual quality comparable to that of per-scene methods but also significantly enhances efficiency and applicability, marking a notable advancement in the field of 3D style transfer.