Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Pixel-Wise Confidences for Stereo Disparities Using Recurrent Neural Networks

: Gul, Muhammad Shahzeb Khan; Bätz, Michel; Keinert, Joachim

Volltext urn:nbn:de:0011-n-5813126 (880 KByte PDF)
MD5 Fingerprint: e409f81ec4f8414f02e7e8c499c91de3
Erstellt am: 17.3.2020

British Machine Vision Association -BMVA-:
30th British Machine Vision Conference, BMVC 2019. Detailed Programme. Online resource : 9th-12th September 2019, Cardiff
Cardiff, 2019
13 S.
British Machine Vision Conference (BMVC) <30, 2019, Cardiff>
European Commission EC
H2020; 765911; RealVision
Hyperrealistic Imaging Experience
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IIS ()
Lichtfeld; Image Based Rendering; computational imaging; Bildverarbeitung; Algorithmen; 3D Bildverarbeitung

One of the inherent problems with stereo disparity estimation algorithms is the lack of reliability information for the computed disparities. As a consequence, errors from the initial disparity maps are propagated to the following processing steps such as view rendering. Nowadays, confidence measures belong to the most popular techniques because of their capability to detect disparity outliers. Recently, convolutional neural network based confidence measures achieved best results by directly processing initial disparity maps. In contrast to existing convolutional neural network based methods, we propose a novel recurrent neural network architecture to compute confidences for different stereo matching algorithms. To maintain a low complexity the confidence for a given pixel is purely computed from its associated matching costs without considering any additional neighbouring pixels. As compared to the state-of-the-art confidence prediction methods leveraging convolutional neural networks, the proposed network is simpler and smaller in terms of size (reduction of the number of trainable parameters by almost 3-4 orders of magnitude). Moreover, the experimental results on three well-known datasets as well as with two popular stereo algorithms clearly highlight that the proposed approach outperforms state-of-the-art confidence estimation techniques.