论文标题
基于对象的照明估计通过渲染感知神经网络
Object-based Illumination Estimation with Rendering-aware Neural Networks
论文作者
论文摘要
我们提出了一种从单个对象的RGBD出现及其本地图像区域的RGBD出现的计划。常规的反渲染对实时应用程序的计算要求太高了，纯粹基于学习的技术的性能可能会受到单个对象可用的微薄输入数据的限制。为了解决这些问题，我们提出了一种方法，该方法利用了从反向渲染来限制解决方案的物理原理，同时还利用神经网络来加快其处理中更昂贵的计算昂贵部分，以提高噪声输入数据的鲁棒性以及提高时间稳定和空间稳定性。这会导致一个渲染感知系统，该系统以高准确性和实时估算对象处的局部照明分布。通过估计的照明，可以在AR场景中呈现虚拟对象，并具有与真实场景一致的阴影，从而改善了现实主义。
We present a scheme for fast environment light estimation from the RGBD appearance of individual objects and their local image areas. Conventional inverse rendering is too computationally demanding for real-time applications, and the performance of purely learning-based techniques may be limited by the meager input data available from individual objects. To address these issues, we propose an approach that takes advantage of physical principles from inverse rendering to constrain the solution, while also utilizing neural networks to expedite the more computationally expensive portions of its processing, to increase robustness to noisy input data as well as to improve temporal and spatial stability. This results in a rendering-aware system that estimates the local illumination distribution at an object with high accuracy and in real time. With the estimated lighting, virtual objects can be rendered in AR scenarios with shading that is consistent to the real scene, leading to improved realism.
