追踪、修复与重绘：基于渐进式纹理填充的主体驱动式三维与四维生成技术

摘要

当前的三维/四维生成方法通常以提升真实感、效率与美学表现为优化目标，但往往难以在不同视角下保持主体的语义一致性。基于单张或少量特定主体图像进行生成方法适配（即个性化或主体驱动生成），能够创造出与主体身份特征相符的视觉内容。然而，个性化三维/四维生成领域仍存在大量探索空间。本研究提出TIRE（追踪、修复、重映射）这一创新性主体驱动式三维/四维生成方法：首先对现有三维生成模型输出的初始三维资产进行视频追踪，定位需修改区域；随后采用主体驱动的二维修复模型渐进式填充目标区域；最后将修改后的二维多视角观测结果重映射至三维空间，同时保持全局一致性。大量实验表明，相较于现有先进方法，本方案在三维/四维生成的身份特征保持方面实现显著提升。项目网站详见：https://zsh2000.github.io/track-inpaint-resplat.github.io/。

English

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/.

追踪、修复与重绘：基于渐进式纹理填充的主体驱动式三维与四维生成技术

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

摘要

Support