SKED：草图引导的基于文本的3D编辑
SKED: Sketch-guided Text-based 3D Editing
AI总结：
针对 NeRF 3D场景难以通过文本进行局部交互编辑的问题，本文提出 SKED，利用仅两张不同视图草图与扩散模型语义引导实现3D编辑，并通过新损失保持未编辑区域。
摘要：
文本到图像扩散模型正逐渐被引入计算机图形学，近期推动了开放领域中 Text-to-3D 流程的发展。然而，出于交互式编辑目的，仅通过简单的文本界面对内容进行局部操控可能十分困难。将用户引导的草图与 Text-to-image 流程相结合，可为用户提供更直观的控制。不过，由于最先进的 Text-to-3D 流程依赖来自任意渲染视图的梯度来优化 Neural Radiance Fields（NeRF，神经辐射场），以草图作为条件并不直接。本文提出 SKED，这是一种编辑由 NeRF 表示的3D形状的技术。该技术仅利用来自不同视图的两张引导草图即可改变现有神经场。被编辑区域通过预训练扩散模型遵循提示词语义。为确保生成输出符合所提供的草图，我们提出了新的损失函数，以在保留基础实例密度和辐射度的同时生成所需编辑。我们通过若干定性与定量实验证明了所提方法的有效性。https://sked-paper.github.io/
英文摘要：
Text-to-image diffusion models are gradually introduced into computer graphics, recently enabling the development of Text-to-3D pipelines in an open domain. However, for interactive editing purposes, local manipulations of content through a simplistic textual interface can be arduous. Incorporating user guided sketches with Text-to-image pipelines offers users more intuitive control. Still, as state-of-the-art Text-to-3D pipelines rely on optimizing Neural Radiance Fields (NeRF) through gradients from arbitrary rendering views, conditioning on sketches is not straightforward. In this paper, we present SKED, a technique for editing 3D shapes represented by NeRFs. Our technique utilizes as few as two guiding sketches from different views to alter an existing neural field. The edited region respects the prompt semantics through a pre-trained diffusion model. To ensure the generated output adheres to the provided sketches, we propose novel loss functions to generate the desired edits while preserving the density and radiance of the base instance. We demonstrate the effectiveness of our proposed method through several qualitative and quantitative experiments. https://sked-paper.github.io/
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。
