Inpaint4DNeRF：基于生成扩散模型的可提示时空NeRF修复
Inpaint4DNeRF: Promptable Spatio-Temporal NeRF Inpainting with Generative Diffusion Models
AI总结：
本文提出Inpaint4DNeRF框架，利用稳定扩散模型生成种子图像及3D几何代理，解决静态与动态NeRF场景中的时空修复与多视角一致性问题。
摘要：
当前的神经辐射场（NeRF）能生成逼真的新视角。为编辑NeRF表示的3D场景，随着生成模型的出现，本文提出Inpaint4DNeRF，利用最先进的稳定扩散模型（如ControlNet）直接生成底层完整背景内容，无论静态或动态。此生成式NeRF修复方法的关键优势有二。首先，粗略掩码传播后，为补全先前被遮挡的内容，可单独生成一小部分内容合理的完整图像，称为种子图像，由此推导出简单的3D几何代理。其次，剩余问题便是所有完整图像间的3D多视角一致性，现由种子图像及其3D代理引导。无需额外技巧，生成式Inpaint4DNeRF基线框架具有通用性，可轻松扩展至4D动态NeRF，时间一致性能以与多视角一致性类似的方式自然处理。
英文摘要：
Current Neural Radiance Fields (NeRF) can generate photorealistic novel views. For editing 3D scenes represented by NeRF, with the advent of generative models, this paper proposes Inpaint4DNeRF to capitalize on state-of-the-art stable diffusion models (e.g., ControlNet) for direct generation of the underlying completed background content, regardless of static or dynamic. The key advantages of this generative approach for NeRF inpainting are twofold. First, after rough mask propagation, to complete or fill in previously occluded content, we can individually generate a small subset of completed images with plausible content, called seed images, from which simple 3D geometry proxies can be derived. Second and the remaining problem is thus 3D multiview consistency among all completed images, now guided by the seed images and their 3D proxies. Without other bells and whistles, our generative Inpaint4DNeRF baseline framework is general which can be readily extended to 4D dynamic NeRFs, where temporal consistency can be naturally handled in a similar way as our multiview consistency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
