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.
|Title of host publication||2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings|
|Publisher||IEEE Computer Society|
|Number of pages||5|
|State||Published - 2 Jul 2017|
|Event||24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China|
Duration: 17 Sep 2017 → 20 Sep 2017
|Name||Proceedings - International Conference on Image Processing, ICIP|
|Conference||24th IEEE International Conference on Image Processing, ICIP 2017|
|Period||17/09/17 → 20/09/17|
Bibliographical noteFunding Information:
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP) (NRF-2016R1A2A2A05921659).
© 2017 IEEE.
- Confidence prediction
- Convolutional neural networks
- Depth refinement
- Matching probability
- Stereo matching