A novel method is proposed in this paper for light field depth estimation by using a convolutional neural network. Manyapproaches have been proposed to make light field depth estimation, while most of them have a contradiction betweenaccuracy and runtime. In order to solve this problem, we proposed a method which can get more accurate light field depthestimation results with faster speed. First, the light field data is augmented by proposed method considering the light fieldgeometry. Because of the large amount of the light field data, the number of images needs to be reduced appropriately toimprove the operation speed, while maintaining the confidence of the estimation. Next, light field images are inputted intoour network after data augmentation. The features of the images are extracted during the process, which could be used tocalculate the disparity value. Finally, our network can generate an accurate depth map from the input light field image aftertraining. Using this accurate depth map, the 3D structure in real world could be accurately reconstructed. Our method isverified by the HCI 4D Light Field Benchmark and real-world light field images captured with a Lytro light field camera.
展开▼
机译:本文提出了一种新的方法,用于使用卷积神经网络进行光场深度估计。许多已经提出了方法来制造光场深度估计,而大多数人之间的大多数都有矛盾准确性和运行时。为了解决这个问题,我们提出了一种可以获得更准确的光场深度的方法估计速度更快。首先,考虑光场的提出方法来增强光场数据几何学。由于大量的光场数据,需要适当地减少图像的数量提高操作速度,同时保持估计的置信度。接下来,输入光场图像我们的网络经过数据增强。在该过程中提取图像的特征,该过程可用于计算视差值。最后,我们的网络可以从输入光场图像生成精确的深度映射训练。使用这种精确的深度图,可以准确地重建现实世界中的3D结构。我们的方法是由HCI 4D灯场基准和现实世界灯场图像验证,使用Lytro Light Field Camera捕获。
展开▼