Neural Disparity Refinement

Fabio Tosi, Filippo Aleotti, Pierluigi Zama Ramirez, Matteo Poggi, Samuele Salti, Stefano Mattoccia, Luigi Di Stefano

Abstract

We propose a framework that combines traditional, hand-crafted algorithms and recent advances in deep learning to obtain high-quality, high-resolution disparity maps from stereo images. By casting the refinement process as a continuous feature sampling strategy, our neural disparity refinement network can estimate an enhanced disparity map at any output resolution. Our solution can process any disparity map produced by classical stereo algorithms, as well as those predicted by modern stereo networks or even different depth-from-images approaches, such as the COLMAP structure-from-motion pipeline. Nonetheless, when deployed in the former configuration, our framework performs at its best in terms of zero-shot generalization from synthetic to real images. Moreover, its continuous formulation allows for easily handling the unbalanced stereo setup very diffused in mobile phones.
BibTeX
@article{tosi2024neural,
  author = {Fabio Tosi and Filippo Aleotti and Pierluigi Zama Ramirez and Matteo Poggi and Samuele Salti and Stefano Mattoccia and Luigi Di Stefano},
  title = {{Neural Disparity Refinement}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2024},
  doi = {10.1109/tpami.2024.3411292},
}

Loading related content...

Figure