TY - GEN
T1 - FGCNet
T2 - 21st IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2022
AU - Liu, Liu
AU - Pan, Liyuan
AU - Luo, Wei
AU - Xu, Qichao
AU - Wen, Yuxiang
AU - Li, Jiangwei
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper proposes a fast graph convolution network (FGCNet) to match two sets of sparse features. FGCNet has three new modules connected in sequence: (i) a local graph convolution block takes point-wise features as inputs and encodes local contextual infor-mation to extract local features; (ii) a fast graph message-passing network takes local features as inputs, encodes two-view global contextual information, to improve the discriminativeness of point-wise features; (iii) a preemptive optimal matching layer takes point-wise features as inputs, regress point-wise matchedness scores and es-timate a 2D joint probability matrix, with each item describes the matchedness of a feature correspondence. We validate the proposed method on three AR/VR related tasks: two-view matching, 3D re-construction and visual localization. Experiments show that our method significantly reduces the computational complexity compared with state-of-the-art methods, while achieving competitive or better performance.
AB - This paper proposes a fast graph convolution network (FGCNet) to match two sets of sparse features. FGCNet has three new modules connected in sequence: (i) a local graph convolution block takes point-wise features as inputs and encodes local contextual infor-mation to extract local features; (ii) a fast graph message-passing network takes local features as inputs, encodes two-view global contextual information, to improve the discriminativeness of point-wise features; (iii) a preemptive optimal matching layer takes point-wise features as inputs, regress point-wise matchedness scores and es-timate a 2D joint probability matrix, with each item describes the matchedness of a feature correspondence. We validate the proposed method on three AR/VR related tasks: two-view matching, 3D re-construction and visual localization. Experiments show that our method significantly reduces the computational complexity compared with state-of-the-art methods, while achieving competitive or better performance.
KW - Two-view matching-3D reconstruction-Visual localization-Graph convolution
UR - http://www.scopus.com/inward/record.url?scp=85146056488&partnerID=8YFLogxK
U2 - 10.1109/ISMAR-Adjunct57072.2022.00096
DO - 10.1109/ISMAR-Adjunct57072.2022.00096
M3 - Conference contribution
AN - SCOPUS:85146056488
T3 - Proceedings - 2022 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2022
SP - 453
EP - 458
BT - Proceedings - 2022 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2022
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 17 October 2022 through 21 October 2022
ER -