Stylizing 3D Scene via Implicit Representation and HyperNetwork

TL;DR

This paper introduces a novel framework combining neural radiance fields and hypernetworks to stylize 3D scenes, enabling consistent, high-quality stylized view synthesis from arbitrary angles.

Contribution

It proposes a joint implicit representation and hypernetwork approach for 3D scene stylization, addressing previous issues of blurriness and inconsistency in view synthesis.

Findings

Produces faithful stylization with consistent appearance across views

Outperforms existing methods in quality and consistency

Effective two-stage training and patch sampling strategies

Abstract

In this work, we aim to address the 3D scene stylization problem - generating stylized images of the scene at arbitrary novel view angles. A straightforward solution is to combine existing novel view synthesis and image/video style transfer approaches, which often leads to blurry results or inconsistent appearance. Inspired by the high-quality results of the neural radiance fields (NeRF) method, we propose a joint framework to directly render novel views with the desired style. Our framework consists of two components: an implicit representation of the 3D scene with the neural radiance fields model, and a hypernetwork to transfer the style information into the scene representation. In particular, our implicit representation model disentangles the scene into the geometry and appearance branches, and the hypernetwork learns to predict the parameters of the appearance branch from the reference style image. To alleviate the training difficulties and memory burden, we propose a two-stage training procedure and a patch sub-sampling approach to optimize the style and content losses with the neural radiance fields model. After optimization, our model is able to render consistent novel views at arbitrary view angles with arbitrary style. Both quantitative evaluation and human subject study have demonstrated that the proposed method generates faithful stylization results with consistent appearance across different views.