Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its usefulness in general-purpose applications. In this paper, we make progress toward understanding the behavior of SDS and its variants by viewing them as solving an optimal-cost transport path from a source distribution to a target distribution. Under this new interpretation, these methods seek to transport corrupted images (source) to the natural image distribution (target). We argue that current methods' characteristic artifacts are caused by (1) linear approximation of the optimal path and (2) poor estimates of the source distribution. We show that calibrating the text conditioning of the source distribution can produce high-quality generation and translation results with little extra overhead. Our method can be easily applied across many domains, matching or beating the performance of specialized methods. We demonstrate its utility in text-to-2D, text-based NeRF optimization, translating paintings to real images, optical illusion generation, and 3D sketch-to-real. We compare our method to existing approaches for score distillation sampling and show that it can produce high-frequency details with realistic colors.

翻译：分数蒸馏采样（SDS）已被证明是一种重要工具，它使得在大规模扩散先验模型应用于数据稀缺领域的任务成为可能。然而，SDS存在一系列特征性伪影，限制了其在通用场景中的应用。本文通过将SDS及其变体视为求解从源分布到目标分布的最优代价传输路径，推进了对这些方法行为的理解。在这一新诠释下，这些方法旨在将退化图像（源）传输至自然图像分布（目标）。我们认为现有方法的特征性伪影源于：（1）对最优路径的线性近似；（2）对源分布的估计偏差。研究表明，通过校准源分布的文本条件设定，能够以极低额外成本实现高质量的生成与转换效果。本方法可轻松应用于多领域，其性能与专用方法相当或更优。我们在文本到二维图像生成、基于文本的神经辐射场优化、绘画转真实图像、视错觉生成及三维草图转真实场景等任务中验证了其有效性。通过与现有分数蒸馏采样方法的对比实验，证明本方法能够生成具有真实色彩的高频细节。