NeRFiller: Completing Scenes via Generative 3D Inpainting
CoRR(2023)
摘要
We propose NeRFiller, an approach that completes missing portions of a 3D
capture via generative 3D inpainting using off-the-shelf 2D visual generative
models. Often parts of a captured 3D scene or object are missing due to mesh
reconstruction failures or a lack of observations (e.g., contact regions, such
as the bottom of objects, or hard-to-reach areas). We approach this challenging
3D inpainting problem by leveraging a 2D inpainting diffusion model. We
identify a surprising behavior of these models, where they generate more 3D
consistent inpaints when images form a 2$\times$2 grid, and show how to
generalize this behavior to more than four images. We then present an iterative
framework to distill these inpainted regions into a single consistent 3D scene.
In contrast to related works, we focus on completing scenes rather than
deleting foreground objects, and our approach does not require tight 2D object
masks or text. We compare our approach to relevant baselines adapted to our
setting on a variety of scenes, where NeRFiller creates the most 3D consistent
and plausible scene completions. Our project page is at
https://ethanweber.me/nerfiller.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要