G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Styles

TL;DR

G3DST introduces a generalizable NeRF-based method for 3D style transfer that produces high-quality, multi-view consistent stylized images across scenes without per-scene optimization, significantly improving efficiency and applicability.

Contribution

The paper proposes a novel hypernetwork-enhanced generalizable NeRF model enabling real-time 3D style transfer across diverse scenes and styles without scene-specific training.

Findings

Achieves high-quality stylized novel views comparable to scene-specific methods

Ensures multi-view consistency through a flow-based loss

Significantly improves efficiency and generalization in 3D style transfer

Abstract

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.