Single Image Multi-Spectral Photometric Stereo Using a Split U-Shaped CNN
Single Image Multi-Spectral Photometric Stereo Using a Split U-Shaped CNN
复制标题
使用分割 U 形 CNN 的单图像多光谱光度立体
DOI：
10.1109/cvprw.2019.00065
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Daniel Soukup
中科院分区：
文献类型：
--
作者：
Doris Antensteiner;S. Stolc;Daniel Soukup
我们提出了一个系统，使用三种不同颜色的照明源从单张图像中提取表面方向和反照率。光度立体允许提取局部表面信息，例如法线或梯度。传统上，局部方向和反照率是使用相同视角和不同照明方向下的多次采集来计算的。在移动物体的应用中，采集和处理速度至关重要，这样的设置不太适合。我们提出在定义的照明方向下使用三种不同颜色的光源进行单次分解。为了实现快速且正则化的推理，我们构建了一个分裂的 U 形卷积神经网络，该网络采用单次输入并同时估计表面方向和反照率。
We present a system to extract surface orientation and albedos from a single shot image using three differently colored illumination sources. Photometric stereo allows one to extract local surface information such as normals or gradients. Traditionally, the local orientations and albedos are computed using serveral acquisitions of the same viewing angle and under varying illumination directions. In applications with moving objects, where the acquisition-as well as processing speed are essential, such setups are poorly suited. We propose a single shot decomposition using three differently colored light sources under defined illumination directions. To allow for a fast and regularized inference, we built a split U-shaped convolutional neural network, which takes a single shot input and estimates both the surface orientation and albedo simultaneously.