Deep stereo confidence prediction for depth estimation

Sunok Kim, Dongbo Min, Bumsub Ham, Seungryong Kim, Kwanghoon SohnICIP 2017 · OpenReview

Abstract

We present a novel method that predicts a confidence to improve the accuracy of an estimated depth map in stereo matching. In contrast to existing learning based approaches relying on hand-crafted confidence features, we cast this problem into a convolutional neural network, learned using both a matching cost volume and its associated disparity map. As the size of the matching cost volume varies depending on a search range of stereo image pairs, we propose to use a top-K matching probability volume layer so that an input size for convolutional layers remains unchanged. Experimental results demonstrate that the proposed method outperforms the state-of-the-art confidence estimation approaches on various benchmarks.
BibTeX
@inproceedings{kim2017deep,
  author = {Sunok Kim and Dongbo Min and Bumsub Ham and Seungryong Kim and Kwanghoon Sohn},
  title = {{Deep stereo confidence prediction for depth estimation}},
  booktitle = {ICIP},
  year = {2017},
  url = {https://openreview.net/forum?id=ukb_5E-WU4i},
}

Loading related content...

Figure