Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Wangduo Xie"'
Publikováno v:
IET Computer Vision, Vol 17, Iss 6, Pp 615-625 (2023)
Abstract In the current stereo matching field, the accuracy of the derived disparity map is highly dependent on the processing capability of ill regions. Fortunately, we find that the use of local information will eliminate the negative effects assoc
Externí odkaz:
https://doaj.org/article/07bebdc11b664894adbc0a3dfcc89723
Publikováno v:
2021 IEEE International Conference on Multimedia and Expo (ICME).
Recent deep convolution-based stereo matching methods have shown significant progress. However, most state-of-the-art models achieve high accuracy by using 3D convolutions during cost aggregation, which come with more floating-point computations and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0214438023edfee80b839d7e673dd7ea
https://doi.org/10.1109/icme51207.2021.9428210
https://doi.org/10.1109/icme51207.2021.9428210
Publikováno v:
ICASSP
Nowadays, CNN-based stereo matching methods achieved remarkable performance, and how to efficiently exploit contextual information in cost aggregation stage is the key to improve performance. In this paper, we propose a simple yet efficient network n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f8ab0e8c8f116c3db217895d96c8067
https://doi.org/10.1109/icassp39728.2021.9414381
https://doi.org/10.1109/icassp39728.2021.9414381
Publikováno v:
ICASSP
Nowadays CNN-based stereo image super-resolution(SR) methods have obtained remarkable performance. However, most of existing methods only superficially portrayed the low layer features without considering the uneven distribution of information, which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aa0e944b7a61c140fb50d92d5374ff62
https://doi.org/10.1109/icassp40776.2020.9054687
https://doi.org/10.1109/icassp40776.2020.9054687