基于逆向过程建模的单视图 3D 重建
Single-view 3D reconstruction via inverse procedural modeling
AI总结:
提出基于逆向过程建模的 3D 重建方法,结合可微渲染与可微及不可微过程生成器,在单张或少量输入图像下实现高精度且无伪影的复杂对象重建。
摘要:
我们提出了一种通过逆向过程建模进行 3D 重建的方法,并研究了该方法的两种变体。第一种方案是使用遗传算法拟合输入参数集。我们在树模型这种复杂对象上展示了工作成果,大多数现有方法无法处理此类对象的重建。第二种方案通过在 memetic algorithm 中使用梯度、可微渲染以及可微过程生成器,显著提高了精度。我们的工作有 2 个主要贡献。首先,我们提出了一种将可微渲染与逆向过程建模相结合的方法。这使得在只有少量输入图像可用时(即使是单张图像),我们能够比现有方法更准确地重建 3D 模型。其次,我们在单一框架中结合了可微和不可微过程生成器,这使我们能够将逆向过程建模应用于相当复杂的生成器:当梯度可用时,重建是精确的;当梯度不可用时,重建是近似的,但始终具有高质量且没有视觉伪影。
英文摘要:
We propose an approach to 3D reconstruction via inverse procedural modeling and investigate two variants of this approach. The first option consists in the fitting set of input parameters using a genetic algorithm. We demonstrate the results of our work on tree models, complex objects, with the reconstruction of which most existing methods cannot handle. The second option allows us to significantly improve the precision by using gradients within memetic algorithm, differentiable rendering and also differentiable procedural generators. In our work we see 2 main contributions. First, we propose a method to join differentiable rendering and inverse procedural modeling. This gives us an opportunity to reconstruct 3D model more accurately than existing approaches when a small number of input images are available (even for single image). Second, we join both differentiable and non-differentiable procedural generators in a single framework which allow us to apply inverse procedural modeling to fairly complex generators: when gradient is available, reconstructions is precise, when gradient is not available, reconstruction is approximate, but always high quality without visual artifacts.
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。