利用变分分数保持身份以实现通用3D编辑
Preserving Identity with Variational Score for General-purpose 3D Editing
AI总结：
本文提出基于扩散模型的优化方法 Piva，通过额外的变分分数蒸馏项保持身份，解决 DDS 细节丢失与过饱和问题，实现零样本2D图像和3D神经场编辑。
摘要：
我们提出了 Piva（Preserving Identity with Variational Score Distillation，利用变分分数蒸馏保持身份），这是一种基于扩散模型编辑图像和3D模型的新型优化方法。具体而言，我们的方法受到近期提出的2D图像编辑方法 Delta Denoising Score（DDS）的启发。我们指出了 DDS 在2D和3D编辑中的局限，这些局限会导致细节丢失和过度饱和。为解决该问题，我们提出一个额外的分数蒸馏项，用于强制保持身份。这带来了更稳定的编辑过程，可逐步优化 NeRF 模型，使其匹配目标提示，同时保留关键的输入特征。我们在零样本图像和神经场编辑中证明了方法的有效性。我们的方法成功改变视觉属性，添加细微和显著的结构元素，转换形状，并在标准2D和3D编辑基准上取得具有竞争力的结果。此外，该方法不施加遮罩或预训练等约束，因此可兼容多种预训练扩散模型。这支持无需将神经场转换为网格的多功能编辑，提供更友好的用户体验。
英文摘要：
We present Piva (Preserving Identity with Variational Score Distillation), a novel optimization-based method for editing images and 3D models based on diffusion models. Specifically, our approach is inspired by the recently proposed method for 2D image editing - Delta Denoising Score (DDS). We pinpoint the limitations in DDS for 2D and 3D editing, which causes detail loss and over-saturation. To address this, we propose an additional score distillation term that enforces identity preservation. This results in a more stable editing process, gradually optimizing NeRF models to match target prompts while retaining crucial input characteristics. We demonstrate the effectiveness of our approach in zero-shot image and neural field editing. Our method successfully alters visual attributes, adds both subtle and substantial structural elements, translates shapes, and achieves competitive results on standard 2D and 3D editing benchmarks. Additionally, our method imposes no constraints like masking or pre-training, making it compatible with a wide range of pre-trained diffusion models. This allows for versatile editing without needing neural field-to-mesh conversion, offering a more user-friendly experience.
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。
