重新思考用于三维编辑与生成的分数蒸馏采样
Rethinking Score Distilling Sampling for 3D Editing and Generation
AI总结：
本文提出统一蒸馏采样UDS，通过统一SDS及其变体中的底层梯度项，使单一方法同时支持高质量三维资产生成与编辑，实验证明其在生成细节和编辑效果上均优于基线方法。
摘要：
分数蒸馏采样（Score Distillation Sampling, SDS）通过利用二维扩散模型的优势，已成为文本到三维生成领域的一种重要方法。然而，SDS仅限于生成任务，缺乏编辑现有三维资产的能力。相反，引入编辑能力的SDS变体往往无法有效生成新的三维资产。在本工作中，我们观察到SDS及其变体中的生成过程与编辑过程具有统一的底层梯度项。基于这一认识，我们提出了统一蒸馏采样（Unified Distillation Sampling, UDS），这是一种能够无缝整合三维资产生成与编辑的方法。本质上，UDS对原始SDS方法中使用的梯度项进行了精炼，将其统一以同时支持生成与编辑两项任务。大量实验表明，UDS不仅在生成细节更丰富的三维资产方面优于基线方法，而且在编辑任务中也表现出色，从而弥合了三维生成与编辑之间的差距。代码可在以下地址获取：https://github.com/xingy038/UDS。
英文摘要：
Score Distillation Sampling (SDS) has emerged as a prominent method for text-to-3D generation by leveraging the strengths of 2D diffusion models. However, SDS is limited to generation tasks and lacks the capability to edit existing 3D assets. Conversely, variants of SDS that introduce editing capabilities often can not generate new 3D assets effectively. In this work, we observe that the processes of generation and editing within SDS and its variants have unified underlying gradient terms. Building on this insight, we propose Unified Distillation Sampling (UDS), a method that seamlessly integrates both the generation and editing of 3D assets. Essentially, UDS refines the gradient terms used in vanilla SDS methods, unifying them to support both tasks. Extensive experiments demonstrate that UDS not only outperforms baseline methods in generating 3D assets with richer details but also excels in editing tasks, thereby bridging the gap between 3D generation and editing. The code is available on: https://github.com/xingy038/UDS.
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。
