Reference-based Controllable Scene Stylization with Gaussian Splatting
Yiqun Mei, Jiacong Xu, Vishal M. Patel

TL;DR
This paper introduces ReGS, a real-time reference-based scene stylization method that adapts 3D Gaussian Splatting for efficient view synthesis, addressing the challenge of appearance editing while maintaining geometric consistency.
Contribution
ReGS is the first to enable real-time, reference-based scene stylization using 3D Gaussian Splatting with a novel texture-guided control mechanism for appearance editing.
Findings
ReGS achieves state-of-the-art stylization quality.
ReGS enables real-time stylized view synthesis.
The method preserves geometric structure while editing appearance.
Abstract
Referenced-based scene stylization that edits the appearance based on a content-aligned reference image is an emerging research area. Starting with a pretrained neural radiance field (NeRF), existing methods typically learn a novel appearance that matches the given style. Despite their effectiveness, they inherently suffer from time-consuming volume rendering, and thus are impractical for many real-time applications. In this work, we propose ReGS, which adapts 3D Gaussian Splatting (3DGS) for reference-based stylization to enable real-time stylized view synthesis. Editing the appearance of a pretrained 3DGS is challenging as it uses discrete Gaussians as 3D representation, which tightly bind appearance with geometry. Simply optimizing the appearance as prior methods do is often insufficient for modeling continuous textures in the given reference image. To address this challenge, we…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Analysis and Summarization · Computer Graphics and Visualization Techniques · Image Retrieval and Classification Techniques
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
