SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection
This addresses occlusion detection for computer vision applications, offering a novel approach that decouples it from traditional frameworks, though it is incremental in improving existing methods.
The paper tackles the problem of occlusion detection in stereo images and video frames by proposing SymmNet, a symmetric convolutional neural network that directly processes image pairs without prior disparity or motion estimation, achieving state-of-the-art results in detecting stereo and motion occlusion.
Detecting the occlusion from stereo images or video frames is important to many computer vision applications. Previous efforts focus on bundling it with the computation of disparity or optical flow, leading to a chicken-and-egg problem. In this paper, we leverage convolutional neural network to liberate the occlusion detection task from the interleaved, traditional calculation framework. We propose a Symmetric Network (SymmNet) to directly exploit information from an image pair, without estimating disparity or motion in advance. The proposed network is structurally left-right symmetric to learn the binocular occlusion simultaneously, aimed at jointly improving both results. The comprehensive experiments show that our model achieves state-of-the-art results on detecting the stereo and motion occlusion.