Dyn-E：动态神经辐射场的局部外观编辑
Dyn-E: Local Appearance Editing of Dynamic Neural Radiance Fields
AI总结：
针对动态神经辐射场（NeRFs）外观编辑研究匮乏的问题，提出通过操纵单帧像素实现局部外观编辑的框架，引入局部表面表示并结合可逆运动网络，让普通用户轻松编辑动态场景，且在多场景中实现时空一致效果，适用于多种动态NeRF变体。
摘要：
近年来，神经辐射场（NeRFs）的编辑受到了广泛关注，但大多数现有工作聚焦于静态场景，而针对动态场景外观编辑的研究相对匮乏。本文提出一种新颖框架，通过操纵训练视频单帧中的像素来编辑动态NeRFs的局部外观。具体而言，为在保留未编辑区域的同时局部编辑动态NeRFs的外观，我们引入编辑区域的局部表面表示，该表示可插入原始NeRF并与之一起渲染，还能通过学习的可逆运动表示网络扭曲到任意其他帧。使用我们的方法，无专业知识的用户可轻松为动态场景外观添加所需内容。我们在多种场景上广泛评估，结果显示该方法实现了空间和时间上一致的编辑效果，且通用性强，适用于不同变体的动态NeRF表示。
英文摘要：
Recently, the editing of neural radiance fields (NeRFs) has gained considerable attention, but most prior works focus on static scenes while research on the appearance editing of dynamic scenes is relatively lacking. In this paper, we propose a novel framework to edit the local appearance of dynamic NeRFs by manipulating pixels in a single frame of training video. Specifically, to locally edit the appearance of dynamic NeRFs while preserving unedited regions, we introduce a local surface representation of the edited region, which can be inserted into and rendered along with the original NeRF and warped to arbitrary other frames through a learned invertible motion representation network. By employing our method, users without professional expertise can easily add desired content to the appearance of a dynamic scene. We extensively evaluate our approach on various scenes and show that our approach achieves spatially and temporally consistent editing results. Notably, our approach is versatile and applicable to different variants of dynamic NeRF representations.
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。
