StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields

by   Kunhao Liu, et al.

3D style transfer aims to render stylized novel views of a 3D scene with multi-view consistency. However, most existing work suffers from a three-way dilemma over accurate geometry reconstruction, high-quality stylization, and being generalizable to arbitrary new styles. We propose StyleRF (Style Radiance Fields), an innovative 3D style transfer technique that resolves the three-way dilemma by performing style transformation within the feature space of a radiance field. StyleRF employs an explicit grid of high-level features to represent 3D scenes, with which high-fidelity geometry can be reliably restored via volume rendering. In addition, it transforms the grid features according to the reference style which directly leads to high-quality zero-shot style transfer. StyleRF consists of two innovative designs. The first is sampling-invariant content transformation that makes the transformation invariant to the holistic statistics of the sampled 3D points and accordingly ensures multi-view consistency. The second is deferred style transformation of 2D feature maps which is equivalent to the transformation of 3D points but greatly reduces memory footprint without degrading multi-view consistency. Extensive experiments show that StyleRF achieves superior 3D stylization quality with precise geometry reconstruction and it can generalize to various new styles in a zero-shot manner.


page 1

page 3

page 7

page 8


UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scene

3D scenes photorealistic stylization aims to generate photorealistic ima...

Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration

Zero-shot artistic style transfer is an important image synthesis proble...

Monolingual and Cross-lingual Zero-shot Style Transfer

We introduce the task of zero-shot style transfer between different lang...

Locally Stylized Neural Radiance Fields

In recent years, there has been increasing interest in applying stylizat...

ZM-Net: Real-time Zero-shot Image Manipulation Network

Many problems in image processing and computer vision (e.g. colorization...

Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer

Transformer-based models achieve favorable performance in artistic style...

VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial Style Transfer

Current talking face generation methods mainly focus on speech-lip synch...

Code Repositories


[CVPR2023] StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields

view repo

Please sign up or login with your details

Forgot password? Click here to reset