An Effective 3D ResNet Architecture for Stereo Image Retrieval

Abstract

While recent stereo images retrieval techniques have been developed based mainly on statistical approaches, this work aims to investigate deep learning ones. More precisely, our contribution consists in designing a twobranch neural networks to extract deep features from the stereo pair. In this respect, a 3D residual network architecture is first employed to exploit the high correlation existing in the stereo pair. This 3D model is then combined with a 2D one applied to the disparity maps, resulting in deep feature representations of the texture information as well as the depth one. Our experiments, carried out on a large scale stereo image dataset, have shown the good performance of the proposed approach compared to the state-of-the-art methods.