Reconstructing the shape and appearance of real-world objects using measured 2D images has been a long-standing inverse rendering problem. In this paper, we introduce a new analysis-by-synthesis technique capable of producing high-quality reconstructions through robust coarse-to-fine optimization and physics-based differentiable rendering.

中文翻译：

---

使用可微蒙特卡罗渲染的统一形状和 SVBRDF 恢复

使用测量的 2D 图像重建真实世界对象的形状和外观一直是一个长期存在的逆渲染问题。在本文中，我们介绍了一种新的综合分析技术，该技术能够通过稳健的粗到细优化和基于物理的可微渲染产生高质量的重建。