Depth estimation from 4D light field videos
This work provides an incremental improvement to depth estimation for computer vision researchers working with light field data, particularly in dynamic scenes.
This paper addresses depth estimation from 4D light field videos, a task previously limited to static images. The authors propose an end-to-end neural network and a synthetic dataset, demonstrating that temporal information improves depth estimation accuracy in noisy regions.
Depth (disparity) estimation from 4D Light Field (LF) images has been a research topic for the last couple of years. Most studies have focused on depth estimation from static 4D LF images while not considering temporal information, i.e., LF videos. This paper proposes an end-to-end neural network architecture for depth estimation from 4D LF videos. This study also constructs a medium-scale synthetic 4D LF video dataset that can be used for training deep learning-based methods. Experimental results using synthetic and real-world 4D LF videos show that temporal information contributes to the improvement of depth estimation accuracy in noisy regions. Dataset and code is available at: https://mediaeng-lfv.github.io/LFV_Disparity_Estimation