CVDec 10, 2019

DeOccNet: Learning to See Through Foreground Occlusions in Light Fields

arXiv:1912.04459v175 citationsHas Code
AI Analysis

This addresses the light field de-occlusion problem for computer vision applications, presenting a novel deep learning-based method.

The paper tackles the problem of reconstructing background objects occluded in some views of a light field camera by proposing DeOccNet, a deep encoder-decoder network that removes foreground occlusions and achieves superior performance compared to other state-of-the-art methods.

Background objects occluded in some views of a light field (LF) camera can be seen by other views. Consequently, occluded surfaces are possible to be reconstructed from LF images. In this paper, we handle the LF de-occlusion (LF-DeOcc) problem using a deep encoder-decoder network (namely, DeOccNet). In our method, sub-aperture images (SAIs) are first given to the encoder to incorporate both spatial and angular information. The encoded representations are then used by the decoder to render an occlusionfree center-view SAI. To the best of our knowledge, DeOccNet is the first deep learning-based LF-DeOcc method. To handle the insufficiency of training data, we propose an LF synthesis approach to embed selected occlusion masks into existing LF images. Besides, several synthetic and realworld LFs are developed for performance evaluation. Experimental results show that, after training on the generated data, our DeOccNet can effectively remove foreground occlusions and achieves superior performance as compared to other state-of-the-art methods. Source codes are available at: https://github.com/YingqianWang/DeOccNet.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes