CasTex：通过显式纹理映射和基于物理的着色进行级联文本到纹理合成
CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading
AI总结：
CasTex通过级联扩散模型实现文本到纹理合成，采用显式纹理参数化提升生成质量，优于现有优化方法。
摘要：
本文研究了使用扩散模型进行文本到纹理合成，以生成基于物理的纹理映射。我们的目标是在变化的光照条件下实现逼真的模型外观。任务中一个显著的解决方案是分数蒸馏采样。它允许在可微的光栅化和着色管道下通过梯度指导恢复复杂的纹理。然而，在实践中，上述解决方案结合广泛使用的潜在扩散模型会产生严重的视觉伪影，并需要额外的正则化，例如隐式纹理参数化。作为一种更直接的替代方法，我们提出了一种使用级联扩散模型进行纹理合成（CasTex）的方法。在我们的设置中，分数蒸馏采样能够直接生成高质量的纹理。特别是，我们能够放弃隐式纹理参数化，转而使用显式参数化以提高过程。在实验中，我们展示了我们的方法在公开的纹理合成基准上显著优于最先进的优化方法。
英文摘要：
This work investigates text-to-texture synthesis using diffusion models to generate physically-based texture maps. We aim to achieve realistic model appearances under varying lighting conditions. A prominent solution for the task is score distillation sampling. It allows recovering a complex texture using gradient guidance given a differentiable rasterization and shading pipeline. However, in practice, the aforementioned solution in conjunction with the widespread latent diffusion models produces severe visual artifacts and requires additional regularization such as implicit texture parameterization. As a more direct alternative, we propose an approach using cascaded diffusion models for texture synthesis (CasTex). In our setup, score distillation sampling yields high-quality textures out-of-the box. In particular, we were able to omit implicit texture parameterization in favor of an explicit parameterization to improve the procedure. In the experiments, we show that our approach significantly outperforms state-of-the-art optimization-based solutions on public texture synthesis benchmarks.
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。
