TY - JOUR
T1 - Improving Stereo Matching Generalization via Fourier-Based Amplitude Transform
AU - Li, Xing
AU - Fan, Yangyu
AU - Rao, Zhibo
AU - Guo, Zhe
AU - Lv, Guoyun
N1 - Publisher Copyright:
© 1994-2012 IEEE.
PY - 2022
Y1 - 2022
N2 - Stereo matching CNNs suffer from performance deteriorate when evaluated under different distributions from training data. Previous domain adaptation/generalization methods are hard to maintain a robust performance in different baselines and usually require difficult adversarial optimization or intricate network structure. To solve this problem, we propose Fourier-based amplitude transform (FAT), mapping the source image to the target style without altering semantic content, which requires no training to perform the domain alignment. Specifically, we leverage the Fourier transform and its inverse to swap the low-frequency amplitude component of the source data with the target data. To effectively map style and relieve the artifacts, we introduce two factors to control the replacing area: the distance of HSV distribution between source and target images; and the difference between the source left image and its warped left image. Experiments testify FAT can significantly bridge domain gaps, making source data distribution closer to target data. Furthermore, when only training on synthetic datasets, FAT can also help different baselines achieve competitive cross-domain generalization capabilities on real datasets.
AB - Stereo matching CNNs suffer from performance deteriorate when evaluated under different distributions from training data. Previous domain adaptation/generalization methods are hard to maintain a robust performance in different baselines and usually require difficult adversarial optimization or intricate network structure. To solve this problem, we propose Fourier-based amplitude transform (FAT), mapping the source image to the target style without altering semantic content, which requires no training to perform the domain alignment. Specifically, we leverage the Fourier transform and its inverse to swap the low-frequency amplitude component of the source data with the target data. To effectively map style and relieve the artifacts, we introduce two factors to control the replacing area: the distance of HSV distribution between source and target images; and the difference between the source left image and its warped left image. Experiments testify FAT can significantly bridge domain gaps, making source data distribution closer to target data. Furthermore, when only training on synthetic datasets, FAT can also help different baselines achieve competitive cross-domain generalization capabilities on real datasets.
KW - cross-domain generalization capability
KW - Fourier-based amplitude transform
KW - Stereo matching
UR - http://www.scopus.com/inward/record.url?scp=85131716085&partnerID=8YFLogxK
U2 - 10.1109/LSP.2022.3180306
DO - 10.1109/LSP.2022.3180306
M3 - 文章
AN - SCOPUS:85131716085
SN - 1070-9908
VL - 29
SP - 1362
EP - 1366
JO - IEEE Signal Processing Letters
JF - IEEE Signal Processing Letters
ER -