DreamCatalyst：通过控制可编辑性与身份保留实现快速高质量3D编辑
DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation
AI总结：
针对现有基于分数蒸馏采样（SDS）的3D编辑方法训练时间长、质量低的问题，提出DreamCatalyst框架，通过解决与扩散模型采样动态的冲突，实现快速且高质量的3D编辑，在NeRF和3DGS编辑任务中性能优于现有方法。
摘要：
分数蒸馏采样（SDS）已成为文本驱动3D编辑任务中的有效框架，利用扩散模型实现3D一致编辑。然而，现有基于SDS的3D编辑方法存在训练时间长、结果质量低的问题。我们发现性能下降的根本原因是其与扩散模型采样动态的冲突。解决该冲突后，我们可将SDS视为通过数据空间采样进行3D编辑的扩散逆过程；而现有方法则简单地利用扩散模型蒸馏分数函数。基于此，我们提出DreamCatalyst框架，通过优化过程近似编辑任务中的扩散逆过程，从而匹配扩散采样动态。该方法提供两种模式：快速模式编辑神经辐射场（NeRF）场景的速度约为当前最先进NeRF编辑方法的23倍；高质量模式的结果更优，速度约为这些方法的8倍。值得注意的是，其高质量模式在速度和质量上均优于当前最先进NeRF编辑方法，且超越最先进3D高斯溅射（3DGS）编辑方法，成为高效且模型无关的3D编辑方案。更多结果见项目页：https://dream-catalyst.github.io。
英文摘要：
Score distillation sampling (SDS) has emerged as an effective framework in text-driven 3D editing tasks, leveraging diffusion models for 3D-consistent editing. However, existing SDS-based 3D editing methods suffer from long training times and produce low-quality results. We identify that the root cause of this performance degradation is \textit{their conflict with the sampling dynamics of diffusion models}. Addressing this conflict allows us to treat SDS as a diffusion reverse process for 3D editing via sampling from data space. In contrast, existing methods naively distill the score function using diffusion models. From these insights, we propose DreamCatalyst, a novel framework that considers these sampling dynamics in the SDS framework. Specifically, we devise the optimization process of our DreamCatalyst to approximate the diffusion reverse process in editing tasks, thereby aligning with diffusion sampling dynamics. As a result, DreamCatalyst successfully reduces training time and improves editing quality. Our method offers two modes: (1) a fast mode that edits Neural Radiance Fields (NeRF) scenes approximately 23 times faster than current state-of-the-art NeRF editing methods, and (2) a high-quality mode that produces superior results about 8 times faster than these methods. Notably, our high-quality mode outperforms current state-of-the-art NeRF editing methods in terms of both speed and quality. DreamCatalyst also surpasses the state-of-the-art 3D Gaussian Splatting (3DGS) editing methods, establishing itself as an effective and model-agnostic 3D editing solution. See more extensive results on our project page: https://dream-catalyst.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。
