RI: Small: Learning-Based Systems for Single-Image Photometric Reconstruction

RI：小型：基于学习的单图像光度重建系统

• 批准号: 0916868
• 负责人: Hassan Foroosh
• 金额: $ 36.3万
• 依托单位: The University of Central Florida Board of Trustees
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-08-15 至 2015-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0916868&HistoricalAwards=false
• 关键词: RI; Small; Learning; Based; Systems

This project focuses on developing algorithms and datasets that can transform photometric reconstruction systems from hand-designed systems into learning-based systems that are optimized on real-world data. Photometric reconstruction systems derive cues from the perceived intensity of different locations on a surface. Shape-from-shading, where the surface is assumed to have a diffuse reflectance, is a well-known example of photometric reconstruction. This project produces the datasets and methods necessary to use machine learning techniques to build models for photometric reconstruction.This learning-based approach enables systems to be optimized on real-world data so that they produce the most accurate results possible. In addition, this learning-based approach enables the development of more sophisticated methods with more parameters than typically used in hand-designed systems. The ability to find optimal parameters in an automated fashion can not only improve existing approaches, such as by incorporating image data more effectively, but can also enable the development of algorithms that push the boundaries of current systems. In particular, algorithms are developed for estimating the shape of objects without knowing the illumination or even trying to explicitly model it.The power of the learning approach cannot be realized without data for training and testing. A major task in this work is the construction of a database of images and ground-truth 3D reconstructions of the objects in the images. The 3D models can be found using an example-based photometric stereo technique.

该项目专注于开发算法和数据集，将光度重建系统从手工设计的系统转变为针对现实世界数据进行优化的基于学习的系统。光度重建系统从表面不同位置的感知强度中获取线索。 阴影形状（假设表面具有漫反射率）是光度重建的一个众所周知的示例。 该项目生成使用机器学习技术构建光度重建模型所需的数据集和方法。这种基于学习的方法使系统能够根据真实数据进行优化，从而产生最准确的结果。 此外，这种基于学习的方法可以开发出比手工设计系统中通常使用的参数更多的更复杂的方法。 以自动化方式找到最佳参数的能力不仅可以改进现有方法（例如通过更有效地合并图像数据），而且还可以开发突破当前系统边界的算法。 特别是，开发了算法来估计物体的形状，而不需要知道照明，甚至不尝试对其进行显式建模。如果没有训练和测试数据，就无法实现学习方法的强大功能。 这项工作的主要任务是构建图像数据库和图像中物体的真实 3D 重建。 可以使用基于示例的光度立体技术找到 3D 模型。