外观驱动的三维模型自动简化
Appearance-Driven Automatic 3D Model Simplification
摘要：
我们提出了一套技术，用于联合优化三角形网格和着色模型，以匹配参考场景的外观。此功能有许多用途，包括保持外观的极其复杂的资产的简化，渲染系统之间的转换，甚至几何场景表示之间的转换。我们遵循并扩展了经典的分析合成技术系列：通过高效的可微分渲染器和现代非线性优化算法，我们的结果能够在类似的观看和照明条件下渲染时最大限度地减少与目标场景的图像空间差异。由于驱动优化的唯一信号是渲染图像的差异，因此该方法具有高度通用性和通用性：它可以轻松支持许多不同的前向渲染模型，如法线映射，空间变化的BRDF，位移映射等。我们输出带有纹理材质的三角形网格，以确保模型在现代图形硬件上高效渲染，并受益于，例如，硬件加速光栅化、光线追踪和过滤纹理查找。我们的系统集成在一个小的Python代码库中，可以应用于高分辨率和大型模型。我们描述了几个用例，包括网格抽取，细节层次生成，无缝网格过滤和聚合几何的近似。
英文摘要：
We present a suite of techniques for jointly optimizing triangle meshes and shading models to match the appearance of reference scenes. This capability has a number of uses, including appearance-preserving simplification of extremely complex assets, conversion between rendering systems, and even conversion between geometric scene representations. We follow and extend the classic analysis-by-synthesis family of techniques: enabled by a highly efficient differentiable renderer and modern nonlinear optimization algorithms, our results are driven to minimize the image-space difference to the target scene when rendered in similar viewing and lighting conditions. As the only signals driving the optimization are differences in rendered images, the approach is highly general and versatile: it easily supports many different forward rendering models such as normal mapping, spatially-varying BRDFs, displacement mapping, etc. Supervision through images only is also key to the ability to easily convert between rendering systems and scene representations. We output triangle meshes with textured materials to ensure that the models render efficiently on modern graphics hardware and benefit from, e.g., hardware-accelerated rasterization, ray tracing, and filtered texture lookups. Our system is integrated in a small Python code base, and can be applied at high resolutions and on large models. We describe several use cases, including mesh decimation, level of detail generation, seamless mesh filtering and approximations of aggregate geometry.
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。
