Hirner, Dominik and Fraundorfer, Friedrich (2021) FC-DCNN: A densely connected neural network for stereo estimation. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2482-2489. ICPR 2020, 10.-15. Jan. 2021, Milan, Italy. doi: 10.1109/ICPR48806.2021.9413281.
![]() |
PDF
9MB |
Official URL: https://ieeexplore.ieee.org/document/9413281
Abstract
We propose a novel lightweight network for stereo estimation. Our network consists of a fully-convolutional densely connected neural network (FC-DCNN) that computes matching costs between rectified image pairs. Our FC-DCNN method learns expressive features and performs some simple but effective postprocessing steps. The densely connected layer structure connects the output of each layer to the input of each subsequent layer. This network structure and the fact that we do not use any fullyconnected layers or 3D convolutions leads to a very lightweight network. The output of this network is used in order to calculate matching costs and create a cost-volume. Instead of using time and memory-inefficient cost-aggregation methods such as semiglobal matching or conditional random fields in order to improve the result, we rely on filtering techniques, namely median filter and guided filter. By computing a left-right consistency check we get rid of inconsistent values. Afterwards we use a watershed foreground-background segmentation on the disparity image with removed inconsistencies. This mask is then used to refine the final prediction. We show that our method works well for both challenging indoor and outdoor scenes by evaluating it on the Middlebury, KITTI and ETH3D benchmarks respectively. Our full framework is available at https://github.com/thedodo/FCDCNN
Item URL in elib: | https://elib.dlr.de/138907/ | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Document Type: | Conference or Workshop Item (Poster) | |||||||||
Title: | FC-DCNN: A densely connected neural network for stereo estimation | |||||||||
Authors: |
| |||||||||
Date: | January 2021 | |||||||||
Journal or Publication Title: | 2020 25th International Conference on Pattern Recognition (ICPR) | |||||||||
Refereed publication: | Yes | |||||||||
Open Access: | Yes | |||||||||
Gold Open Access: | No | |||||||||
In SCOPUS: | No | |||||||||
In ISI Web of Science: | No | |||||||||
DOI : | 10.1109/ICPR48806.2021.9413281 | |||||||||
Page Range: | pp. 2482-2489 | |||||||||
Status: | Published | |||||||||
Keywords: | 3D vision; Deep learning; Neural networks | |||||||||
Event Title: | ICPR 2020 | |||||||||
Event Location: | Milan, Italy | |||||||||
Event Type: | international Conference | |||||||||
Event Dates: | 10.-15. Jan. 2021 | |||||||||
HGF - Research field: | Aeronautics, Space and Transport | |||||||||
HGF - Program: | Transport | |||||||||
HGF - Program Themes: | Road Transport | |||||||||
DLR - Research area: | Transport | |||||||||
DLR - Program: | V ST Straßenverkehr | |||||||||
DLR - Research theme (Project): | V - NGC KoFiF | |||||||||
Location: | Oberpfaffenhofen | |||||||||
Institutes and Institutions: | Remote Sensing Technology Institute > Photogrammetry and Image Analysis | |||||||||
Deposited By: | Knickl, Sabine | |||||||||
Deposited On: | 01 Dec 2020 15:56 | |||||||||
Last Modified: | 11 Jan 2022 09:17 |
Repository Staff Only: item control page