WINGS：基于3D原生生成先验的无参考高斯泼溅修复
WINGS: Reference-Free Gaussian Splatting Inpainting with 3D-Native Generative Priors
浏览论文内容
中文总结 AI 辅助
提出一种原生3D的无参考高斯泼溅修复方法，利用预训练3D先验和结构补全网络直接生成缺失内容，避免多视图不一致并提升速度。
中文摘要 AI 辅助
修复3D高斯泼溅场景是3D编辑中的一个关键挑战，需要在3D空间的掩蔽区域内生成合理的内容。现有方法依赖2D扩散模型生成一个或多个修复后的参考视图，这使其容易受到多视图不一致和优化时间过长等问题的影响。与这些方法不同，我们提出了一种原生在3D中运行的无参考高斯泼溅修复方法。我们的方法利用大型预训练3D先验的嵌入空间，结合结构补全网络，为生成先验提供输入，从而重建缺失区域的几何形状和外观。由于内容生成完全在3D中进行，该方法避免了协调多个修复参考图像不一致性的需要，并且比相关的基于2D的方法更快。我们通过大量实验和用户研究，定性和定量地证明了我们方法的有效性。据我们所知，这是首个在3D原生生成先验的学习表示空间中运行且不依赖修复参考视图的高斯泼溅修复方法。
英文摘要
Inpainting 3D Gaussian Splatting scenes, a key challenge in 3D editing, requires generating plausible content within a masked region of 3D space. Prior approaches rely on 2D diffusion models to produce one or several inpainted reference views, making them susceptible to challenges associated with multi-view inconsistency and lengthy optimization times. Departing from these approaches, we introduce a reference-free Gaussian splatting inpainting method operating natively in 3D. Our method leverages the embedding space of a large, pre-trained 3D prior, combined with a structure completion network to feed a generative prior which reconstructs the missing region's geometry and appearance. Performing content generation entirely in 3D, it avoids the need to reconcile inconsistencies of multiple inpainted reference images, and is faster than related 2D-based methods. We demonstrate the effectiveness of our method qualitatively and quantitatively, through extensive experiments and a user study. To the best of our knowledge, this work is the first Gaussian splatting inpainting method to operate in the learned representation space of a 3D-native generative prior without relying on inpainted reference views.
发表机构
- Adobe
- MILES Team, LAMSADE（MILES团队，LAMSADE）
- Paris Dauphine – PSL University（巴黎第九大学 – PSL大学）
机构由 AI 辅助整理，请以论文原文为准。
