Differentiable rendering is an essential operation in modern vision, allowing inverse graphics approaches to 3D understanding to be utilized in modern machine learning frameworks. Explicit shape representations (voxels, point clouds, or meshes), while relatively easily rendered, often suffer from limited geometric fidelity or topological constraints. On the other hand, implicit representations (occupancy, distance, or radiance fields) preserve greater fidelity, but suffer from complex or inefficient rendering processes, limiting scalability. In this work, we endeavour to address both shortcomings with a novel shape representation that allows fast differentiable rendering within an implicit architecture. Building on implicit distance representations, we define Directed Distance Fields (DDFs), which map an oriented point (position and direction) to surface visibility and depth. Such a field can render a depth map with a single forward pass per pixel, enable differential surface geometry extraction (e.g., surface normals and curvatures) via network derivatives, be easily composed, and permit extraction of classical unsigned distance fields. Using probabilistic DDFs (PDDFs), we show how to model inherent discontinuities in the underlying field. Finally, we apply our method to fitting single shapes, unpaired 3D-aware generative image modelling, and single-image 3D reconstruction tasks, showcasing strong performance with simple architectural components via the versatility of our representation.
翻译:在现代愿景中,差异的产生是现代愿景的一个基本操作,允许现代机器学习框架中使用对3D理解的反向图形方法,在现代机器学习框架中使用3D理解的反向图形方法。清晰的形状表示(微速、点云或meshes)虽然相对容易完成,但往往受到有限的几何忠度或地形限制。另一方面,隐含的表示(占用、距离或亮度字段)保持更大的忠诚,但受复杂或低效率的形成过程的影响,限制可缩放。在这项工作中,我们努力解决两种缺陷,以新的形状表示方式处理缺陷,允许在隐含的架构内快速进行不同的演化。在隐含的距离表示上,我们定义了直接的距离字段(DDDFs),绘制了一个面向地表可见度和深度的定向点(定位和方向)或方向。另一方面,隐含的图示(例如地表常态和曲调)通过网络衍生物进行深度的提取(例如地表常态和曲调),容易组成,并允许提取经典未指派的远程字段。在隐含的DFDFDFS(PDFDFSs)中,我们最后展示了单一的模型的形状的模型的模型,我们展示了单一的模型的外观的外观。