Seal-3D：面向神经辐射场的交互式像素级编辑
Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields
AI总结：
针对现有NeRF编辑方法灵活性、质量、速度不足且无法即时预览的问题，提出Seal-3D交互式像素级编辑系统，通过代理函数与两阶段训练策略，支持多类NeRF骨干的自由编辑，实现约1秒的即时预览与出色编辑效果。
摘要：
随着隐式神经表征即神经辐射场（NeRF）的普及，迫切需要能与隐式3D模型交互的编辑方法，以用于重建场景后处理、3D内容创作等任务。现有研究虽从多维度探索了NeRF编辑，但在编辑灵活性、质量和速度上存在局限，无法提供直接编辑响应与即时预览。核心挑战在于设计一种可局部编辑的神经表征，使其能直接响应编辑指令并即时更新。为填补这一空白，我们提出了一种全新的隐式表征交互式编辑方法与系统Seal-3D，支持用户对各类类NeRF骨干网络进行像素级自由编辑，并可即时预览编辑效果。为实现该目标，我们通过教师模型中负责将编辑指令映射至NeRF模型原始空间的代理函数，以及学生模型采用局部预训练+全局微调的两阶段训练策略，解决了上述挑战。我们构建了一套NeRF编辑系统，可展示多种编辑类型。该系统能以约1秒的交互速度实现出色的编辑效果。
英文摘要：
With the popularity of implicit neural representations, or neural radiance fields (NeRF), there is a pressing need for editing methods to interact with the implicit 3D models for tasks like post-processing reconstructed scenes and 3D content creation. While previous works have explored NeRF editing from various perspectives, they are restricted in editing flexibility, quality, and speed, failing to offer direct editing response and instant preview. The key challenge is to conceive a locally editable neural representation that can directly reflect the editing instructions and update instantly. To bridge the gap, we propose a new interactive editing method and system for implicit representations, called Seal-3D, which allows users to edit NeRF models in a pixel-level and free manner with a wide range of NeRF-like backbone and preview the editing effects instantly. To achieve the effects, the challenges are addressed by our proposed proxy function mapping the editing instructions to the original space of NeRF models in the teacher model and a two-stage training strategy for the student model with local pretraining and global finetuning. A NeRF editing system is built to showcase various editing types. Our system can achieve compelling editing effects with an interactive speed of about 1 second.
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。
