CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields
This work addresses the need for user-specified controllability in creating artistic 3D scenes, which is incremental over prior methods like ARF.
The paper tackles the problem of lacking fine-grained control in 3D artistic style transfer for radiance fields by introducing CoARF, which enables object-specific, compositional, and semantic-aware stylization, achieving superior quality with more precise feature matching as demonstrated in experiments.
Creating artistic 3D scenes can be time-consuming and requires specialized knowledge. To address this, recent works such as ARF, use a radiance field-based approach with style constraints to generate 3D scenes that resemble a style image provided by the user. However, these methods lack fine-grained control over the resulting scenes. In this paper, we introduce Controllable Artistic Radiance Fields (CoARF), a novel algorithm for controllable 3D scene stylization. CoARF enables style transfer for specified objects, compositional 3D style transfer and semantic-aware style transfer. We achieve controllability using segmentation masks with different label-dependent loss functions. We also propose a semantic-aware nearest neighbor matching algorithm to improve the style transfer quality. Our extensive experiments demonstrate that CoARF provides user-specified controllability of style transfer and superior style transfer quality with more precise feature matching.