Learning Light Field Reconstruction from a Single Coded Image
This work addresses the resolution limitation in light field imaging for applications like 3D reconstruction and virtual reality, representing an incremental improvement over existing methods.
The paper tackles the spatio-angular resolution trade-off in light field imaging by reconstructing a full sensor resolution light field from a single coded image using a three-stage deep learning approach, achieving better parallax recovery and outperforming dictionary learning methods both qualitatively and quantitatively.
Light field imaging is a rich way of representing the 3D world around us. However, due to limited sensor resolution capturing light field data inherently poses spatio-angular resolution trade-off. In this paper, we propose a deep learning based solution to tackle the resolution trade-off. Specifically, we reconstruct full sensor resolution light field from a single coded image. We propose to do this in three stages 1) reconstruction of center view from the coded image 2) estimating disparity map from the coded image and center view 3) warping center view using the disparity to generate light field. We propose three neural networks for these stages. Our disparity estimation network is trained in an unsupervised manner alleviating the need for ground truth disparity. Our results demonstrate better recovery of parallax from the coded image. Also, we get better results than dictionary learning based approaches both qualitatively and quatitatively.