Personalize Your Gaussian: Consistent 3D Scene Personalization from a Single Image

TL;DR

This paper introduces CP-GS, a framework that personalizes 3D scenes from a single image by propagating appearance across views, ensuring multi-view and referential consistency for improved 3D scene editing.

Contribution

The paper proposes a novel method combining image-to-3D generation and iterative fine-tuning to overcome viewpoint bias in single-image 3D scene personalization.

Findings

Outperforms existing methods in multi-view consistency

Effectively mitigates viewpoint bias

Produces high-quality personalized 3D scenes

Abstract

Personalizing 3D scenes from a single reference image enables intuitive user-guided editing, which requires achieving both multi-view consistency across perspectives and referential consistency with the input image. However, these goals are particularly challenging due to the viewpoint bias caused by the limited perspective provided in a single image. Lacking the mechanisms to effectively expand reference information beyond the original view, existing methods of image-conditioned 3DGS personalization often suffer from this viewpoint bias and struggle to produce consistent results. Therefore, in this paper, we present Consistent Personalization for 3D Gaussian Splatting (CP-GS), a framework that progressively propagates the single-view reference appearance to novel perspectives. In particular, CP-GS integrates pre-trained image-to-3D generation and iterative LoRA fine-tuning to extract and extend the reference appearance, and finally produces faithful multi-view guidance images and the personalized 3DGS outputs through a view-consistent generation process guided by geometric cues. Extensive experiments on real-world scenes show that our CP-GS effectively mitigates the viewpoint bias, achieving high-quality personalization that significantly outperforms existing methods.