A Data-Driven Regularization Model for Stereo and Flow
Name
Freeman_A data-driven.pdf
Size
8.82 MB
Format
Adobe PDF
Checksum (MD5)
ae8222de2091753840f85d439996b5d9
Author(s)
Freeman, William T.
Wei, Donglai
Liu, Ce
Date Issued
December 2014
Journal
Proceedings of the 2014 2nd International Conference on 3D Vision
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Donglai Wei, Ce Liu, and William T. Freeman. “A Data-Driven Regularization Model for Stereo and Flow.” 2014 2nd International Conference on 3D Vision (December 2014).
Version
Author's final manuscript
Abstract
Data-driven techniques can reliably build semantic correspondence among images. In this paper, we present a new regularization model for stereo or flow through transferring the shape information of the disparity or flow from semantically matched patches in the training database. Compared to previous regularization models based on image appearance alone, we can better resolve local ambiguity of the disparity or flow by considering the semantic information without explicit object modeling. We incorporate this data-driven regularization model into a standard Markov Random Field (MRF) model, inferred with a gradient descent algorithm and learned with a discriminative learning approach. Compared to prior state-of-the-art methods, our full model achieves comparable or better results on the KITTI stereo and flow datasets, and improves results on the Sintel Flow dataset under an online estimation setting.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/3DV.2014.97
