Fast Disparity Estimation from a Single Compressed Light Field Measurement
This work addresses a practical bottleneck for applications using light field technology by reducing storage and processing costs, though it is incremental as it builds on existing compressive sensing and deep learning approaches.
The paper tackles the problem of high computational cost in disparity estimation from compressed light fields by proposing a method that directly estimates disparity from a single compressed measurement, omitting the recovery step. The result is a 20 times faster training and inference compared to traditional methods, with disparity maps comparable to those from reconstructed light fields.
The abundant spatial and angular information from light fields has allowed the development of multiple disparity estimation approaches. However, the acquisition of light fields requires high storage and processing cost, limiting the use of this technology in practical applications. To overcome these drawbacks, the compressive sensing (CS) theory has allowed the development of optical architectures to acquire a single coded light field measurement. This measurement is decoded using an optimization algorithm or deep neural network that requires high computational costs. The traditional approach for disparity estimation from compressed light fields requires first recovering the entire light field and then a post-processing step, thus requiring long times. In contrast, this work proposes a fast disparity estimation from a single compressed measurement by omitting the recovery step required in traditional approaches. Specifically, we propose to jointly optimize an optical architecture for acquiring a single coded light field snapshot and a convolutional neural network (CNN) for estimating the disparity maps. Experimentally, the proposed method estimates disparity maps comparable with those obtained from light fields reconstructed using deep learning approaches. Furthermore, the proposed method is 20 times faster in training and inference than the best method that estimates the disparity from reconstructed light fields.