BriefGPT.xyz
Mar, 2019
极化光深度信息提取
Physics-based Neural Networks for Shape from Polarization
HTML
PDF
Yunhao Ba, Rui Chen, Yiqin Wang, Lei Yan, Boxin Shi...
TL;DR
本研究运用深度学习探讨了极化成形（SfP）问题。通过将物理模型融入神经网络架构中，创新性地兼顾了数据驱动和物理驱动，取得了在不同光照、材质和涂装条件下的最佳测试结果。
Abstract
How should prior knowledge from physics inform a
neural network
solution? We study the blending of physics and
deep learning
in the context of
sh
→