通过生成轨迹实现灵活的3D场景编辑，支持几何与外观同步修改。
Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories
- 基于随机扰动和损失曲面分析自动初始化，提升编辑多样性。
- 利用生成轨迹与身份保持梯度，实现颜色、外观、几何的统一优化。
- 适合需要高自由度3D内容创作的研究者与设计师使用。
文本驱动的扩散模型推动了3D重建与文本控制3D编辑的发展。尽管现有方法在色彩、纹理和风格修改上表现优异，但在大幅几何或外观变化方面仍存在局限。为此，我们提出Perturb-and-Revise，实现多样化的NeRF编辑。首先，通过随机初始化扰动NeRF参数，生成多样化初始状态，扰动程度由局部损失曲面分析自动确定。随后，通过生成轨迹修正编辑后的NeRF，结合生成过程引入身份保持梯度以精细化结果。大量实验表明，该方法能有效、一致地实现3D场景的颜色、外观与几何的灵活编辑。完整360°可视化效果请访问项目页：https://susunghong.github.io/Perturb-and-Revise。
原文摘要 · Abstract (English)
Recent advancements in text-based diffusion models have accelerated progress in 3D reconstruction and text-based 3D editing. Although existing 3D editing methods excel at modifying color, texture, and style, they struggle with extensive geometric or appearance changes, thus limiting their applications. To this end, we propose Perturb-and-Revise, which makes possible a variety of NeRF editing. First, we perturb the NeRF parameters with random initializations to create a versatile initialization. The level of perturbation is determined automatically through analysis of the local loss landscape. Then, we revise the edited NeRF via generative trajectories. Combined with the generative process, we impose identity-preserving gradients to refine the edited NeRF. Extensive experiments demonstrate that Perturb-and-Revise facilitates flexible, effective, and consistent editing of color, appearance, and geometry in 3D. For 360° results, please visit our project page: https://susunghong.github.io/Perturb-and-Revise.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。