统一3D生成与编辑的梯度方法，让文本控制更灵活。
Rethinking Score Distilling Sampling for 3D Editing and Generation
- 通过统一生成与编辑的梯度机制，实现一法双用。
- 在生成任务中细节更丰富，编辑效果更精准。
- 适合需要同时做3D生成和修改的研究者使用。
Score Distillation Sampling (SDS) 作为利用2D扩散模型优势的文本到3D生成主流方法，仅限于生成任务，无法编辑现有3D资产。而部分支持编辑的SDS变体则难以有效生成新3D内容。本文发现生成与编辑在SDS及其变体中具有统一的底层梯度项。基于此，提出统一蒸馏采样（UDS），通过优化原始SDS的梯度项，无缝融合3D生成与编辑能力。大量实验表明，UDS在生成任务中可生成更丰富的细节，在编辑任务中表现更优，有效弥合了3D生成与编辑之间的差距。代码已开源：https://github.com/xingy038/UDS。
原文摘要 · Abstract (English)
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.
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。