PAPER
Fabio Tosi*, Pierluigi Zama Ramirez*, Matteo Poggi*, Samuele Salti, Stefano Mattoccia, Luigi Di Stefano
*Equal Contribution
We address the problem of registering synchronized color (RGB) and multi-spectral (MS) images featuring very different resolution by solving stereo matching correspondences. Purposely, we introduce a novel RGB-MS dataset framing 13 different scenes in indoor environments and providing a total of 34 image pairs annotated with semi-dense, high-resolution ground-truth labels in the form of disparity maps. To tackle the task, we propose a deep learning architecture trained in a self-supervised manner by exploiting a further RGB camera, required only during training data acquisition. In this setup, we can conveniently learn cross-modal matching in the absence of ground-truth labels by distilling knowledge from an easier RGB-RGB matching task based on a collection of about 11K unlabeled image triplets. Experiments show that the proposed pipeline sets a good performance bar (1.16 pixels average registration error) for future research on this novel, challenging task.
CITATION
@inproceedings{tosi2022rgbms,
title={RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation},
author={Tosi, Fabio and Zama Ramirez, Pierluigi and Poggi, Matteo and Salti, Samuele and Di Stefano, Luigi and Mattoccia, Stefano},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
note={CVPR},
year={2022},
}
Given an unbalanced stereo pair composed of a reference high-resolution image L and a target multi-spectral low-resolution image R, our network estimates a disparity map aligned with L by combining cross-spectral cost probabilities computed by a stereo backbone and deep features from L obtained by the feature extractor.
