FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting

Abstract

We present FPGS, a feed-forward photorealistic style transfer method of large-scale radiance fields represented by Gaussian Splatting. FPGS, stylizes large-scale 3D scenes with arbitrary, multiple style reference images without additional optimization while preserving multi-view consistency and real-time rendering speed of 3D Gaussians. Prior arts required tedious per-style optimization or time-consuming per-scene training stage and were limited to small-scale 3D scenes. FPGS efficiently stylizes large-scale 3D scenes by introducing a style-decomposed 3D feature field, which inherits AdaIN's feed-forward stylization machinery, supporting arbitrary style reference images.

Furthermore, FPGS supports multi-reference stylization with the semantic correspondence matching and local AdaIN, which adds diverse user control for 3D scene styles. FPGS also preserves multi-view consistency by applying semantic matching and style transfer processes directly onto queried features in 3D space. In experiments, we demonstrate that FPGS achieves favorable photorealistic quality scene stylization for large-scale static and dynamic 3D scenes with diverse reference images.

Semantic Matching & Local AdaIN

We stylize the large-scale 3D scene with a set of arbitrary reference images, via semantic matching and local AdaIN. We compose a style dictionary consisting of local semantic/style code pairs extracted from the clustered reference images. Using the style dictionary and the semantic features from the scene, we find semantic correspondence between the refernece images and the scene. With the semantic correspondence, we construct semantic-weighted style code and perform local AdaIN for semantic-aware style transfer in a feed-forward manner.

Applications

4D style transfer

Multi-reference style transfer

Scribble-based style transfer

More Results

The LLFF dataset

The BlockNeRF dataset

The Mip-360, Tank & Temples dataset

This is an extension of our prior work, FPRF

BibTeX


      @misc{kim2025fpgsfeedforwardsemanticawarephotorealistic,
        title={FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting}, 
        author={GeonU Kim and Kim Youwang and Lee Hyoseok and Tae-Hyun Oh},
        year={2025},
        eprint={2503.09635},
        archivePrefix={arXiv},
        primaryClass={cs.GR},
        url={https://arxiv.org/abs/2503.09635}, 
  }
}