arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1603.06143cs.GRcs.AI
收藏

神经引导的过程模型:使用神经网络的过程图形程序的分期推理

Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks

Stanford University(斯坦福大学)

Daniel Ritchie, Anna Thomas, Pat Hanrahan, Noah D. Goodman

摘要:

概率推理算法,如顺序蒙特卡罗(SMC)提供了强大的工具,限制在计算机图形学的过程模型,但他们需要许多样本,以产生理想的结果。在本文中,我们将展示如何创建学习如何满足约束的过程模型。我们用神经网络来增强过程模型,神经网络控制模型如何根据迄今为止生成的输出进行随机选择。我们称这种模型为神经引导的程序模型。作为预先计算,我们训练这些模型,以最大限度地提高通过SMC生成的示例输出的可能性。然后,它们被用作高效的SMC重要性采样器,用很少的样本生成高质量的结果。我们评估我们的方法L-系统的模型与基于图像的约束。给定期望的质量阈值,神经引导模型可以比无引导模型快10倍生成令人满意的结果。

英文摘要:

Probabilistic inference algorithms such as Sequential Monte Carlo (SMC) provide powerful tools for constraining procedural models in computer graphics, but they require many samples to produce desirable results. In this paper, we show how to create procedural models which learn how to satisfy constraints. We augment procedural models with neural networks which control how the model makes random choices based on the output it has generated thus far. We call such models neurally-guided procedural models. As a pre-computation, we train these models to maximize the likelihood of example outputs generated via SMC. They are then used as efficient SMC importance samplers, generating high-quality results with very few samples. We evaluate our method on L-system-like models with image-based constraints. Given a desired quality threshold, neurally-guided models can generate satisfactory results up to 10x faster than unguided models.

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。

↑