HCC: Small: Neural Network-based Solvers for Integral Equations in Light Transport

HCC：小型：基于神经网络的光传输积分方程求解器

• 批准号: 2126407
• 负责人: Matthias Zwicker
• 金额: $ 49.72万
• 依托单位: University of Maryland, College Park
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2126407&HistoricalAwards=false
• 关键词: HCC; Small; Neural; Network; based

Neural networks are commonly associated with applications in artificial intelligence such as computer vision, natural language processing, or robotics. They are attractive for these applications because they can model highly complex relationships, such as how colors of millions of individual pixels in an image are related to a high-level description of the image, including the types of objects that are shown etc. This project, however, will leverage the capacity of neural networks to solve numerical simulation problems, with a focus on light transport as the application domain. Novel techniques will be developed to model the complex relationship between 3D virtual environments and corresponding photo-realistic images. This work will enable numerous innovative computer graphics applications, for example in augmented and virtual reality. The new techniques will have broad impact, because they can be adapted and applied to a vast range of related scientific simulation problems. The benefits of the project outcomes include improving the achievable accuracy and enabling the solution of problems at a larger scale and with more complex geometries than is currently possible.This project will develop novel numerical techniques for neural network-based function representations to solve integral equations for light transport problems. The approach will represent continuous solutions using neural networks, and leverage gradient-based numerical solution techniques that minimize appropriate norms of the residuals, after which advanced techniques that improve the performance and accuracy of the baseline approach will be developed and evaluated, including novel neural network architectures that are suitable to effectively represent multi-dimensional functions such as the spatio-angular radiance fields required to solve light and radiative transfer equations, and efficient Monte Carlo sampling and curriculum learning strategies for the residual norms in the numerical problems to allow robust estimation of gradients at lower computational cost. Finally, novel few-shot learning techniques to further accelerate convergence will be investigated.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

神经网络通常与人工智能中的应用相关联，例如计算机视觉，自然语言处理或机器人技术。 它们对这些应用程序很有吸引力，因为它们可以模拟高度复杂的关系，例如图像中数百万个像素的颜色如何与图像的高级描述相关，包括显示的对象类型等。 将开发新的技术来模拟3D虚拟环境和相应的照片逼真的图像之间的复杂关系。这项工作将使许多创新的计算机图形应用程序，例如在增强和虚拟现实。 这些新技术将产生广泛的影响，因为它们可以适应并应用于广泛的相关科学模拟问题。该项目成果的好处包括提高可实现的精度，并使问题的解决方案在更大的规模和更复杂的几何比目前可能的。该项目将开发新的数值技术，为神经网络为基础的函数表示，以解决积分方程的光传输问题。 该方法将使用神经网络表示连续解，并利用基于梯度的数值解技术，最大限度地减少残差的适当范数，然后将开发和评价改进基线方法的性能和准确性的先进技术，包括适于有效地表示多维函数的新颖的神经网络体系结构，解决光和辐射传输方程所需的角辐射场，以及数值问题中剩余范数的有效蒙特卡罗采样和课程学习策略，以允许以较低的计算成本对梯度进行稳健估计。 最后，将研究新的几次学习技术，以进一步加速收敛。该奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

项目成果

Neural radiosity

• DOI: 10.1145/3478513.3480569
• 发表时间: 2021-05
• 期刊: ACM Transactions on Graphics (TOG)
• 作者: Saeed Hadadan;Shuhong Chen;Matthias Zwicker

Inverse Global Illumination using a Neural Radiometric Prior

• DOI: 10.1145/3588432.3591553
• 发表时间: 2023-05
• 期刊: ACM SIGGRAPH 2023 Conference Proceedings
• 作者: Saeed Hadadan;Geng Lin;Jan Novák;Fabrice Rousselle;Matthias Zwicker

Neural Differential Radiance Field: Learning the Differential Space Using a Neural Network

神经微分辐射场：使用神经网络学习微分空间

• 发表时间: 2024
• 期刊: Lecture Notes in Computer Science
• 作者: Hadadan, Saeed;Zwicker, Matthias
• 通讯作者: Zwicker, Matthias