Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling

TL;DR

This paper introduces TIRE, a novel method for subject-driven 3D and 4D generation that enhances identity preservation by tracking, inpainting, and resplatting regions across views, advancing personalized visual content creation.

Contribution

TIRE is the first approach that combines tracking, inpainting, and resplatting to improve identity preservation in 3D/4D generation from limited input images.

Findings

Significantly improves identity preservation over state-of-the-art methods.

Effectively maintains consistency across multiple views in 3D/4D generation.

Demonstrates robustness in personalized subject-driven generation.

Abstract

Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject across different viewpoints. Adapting generation methods with one or few images of a specific subject (also known as Personalization or Subject-driven generation) allows generating visual content that align with the identity of the subject. However, personalized 3D/4D generation is still largely underexplored. In this work, we introduce TIRE (Track, Inpaint, REsplat), a novel method for subject-driven 3D/4D generation. It takes an initial 3D asset produced by an existing 3D generative model as input and uses video tracking to identify the regions that need to be modified. Then, we adopt a subject-driven 2D inpainting model for progressively infilling the identified regions. Finally, we resplat the modified 2D multi-view observations back to 3D while still maintaining consistency. Extensive experiments demonstrate that our approach significantly improves identity preservation in 3D/4D generation compared to state-of-the-art methods. Our project website is available at https://zsh2000.github.io/track-inpaint-resplat.github.io/.