TY - GEN
T1 - Multi-scale Landmark Localization Network for 3D Facial Point Clouds
AU - Guo, Longteng
AU - Ai, Danni
AU - Song, Hong
AU - Yang, Jian
N1 - Publisher Copyright:
© 2021 Association for Computing Machinery. All rights reserved.
PY - 2021/2/26
Y1 - 2021/2/26
N2 - Facial landmark localization on 3D point clouds has been a major concern in the field of computer vision. Recent methods do not feature data containing multiple faces with large-scale variance, which has become increasingly common with the rapid development and wide application of 3D imaging technology. In this paper, we propose a Multi-scale Landmark Localization network for 3D facial point clouds.We evaluate the proposed method on the dataset synthesized by appending and scaling the data in the public dataset BU3DFE to demonstrate the robustness and efficiency. Upon comparing the proposed method with other methods on the standard dataset BU3DFE, in which data only contain one face with smallscale variance, we find that the proposed method shows higher or comparable performance with mean localization errors of 3.34 2.19 mm.
AB - Facial landmark localization on 3D point clouds has been a major concern in the field of computer vision. Recent methods do not feature data containing multiple faces with large-scale variance, which has become increasingly common with the rapid development and wide application of 3D imaging technology. In this paper, we propose a Multi-scale Landmark Localization network for 3D facial point clouds.We evaluate the proposed method on the dataset synthesized by appending and scaling the data in the public dataset BU3DFE to demonstrate the robustness and efficiency. Upon comparing the proposed method with other methods on the standard dataset BU3DFE, in which data only contain one face with smallscale variance, we find that the proposed method shows higher or comparable performance with mean localization errors of 3.34 2.19 mm.
KW - 3D point cloud
KW - Deep learning
KW - Multi-facial landmark localization
KW - Multi-scale faces
UR - https://www.scopus.com/pages/publications/85115979234
U2 - 10.1145/3458380.3458395
DO - 10.1145/3458380.3458395
M3 - Conference contribution
AN - SCOPUS:85115979234
T3 - ACM International Conference Proceeding Series
SP - 86
EP - 93
BT - 2021 5th International Conference on Digital Signal Processing, ICDSP 2021
PB - Association for Computing Machinery
T2 - 5th International Conference on Digital Signal Processing, ICDSP 2021
Y2 - 26 February 2021 through 28 February 2021
ER -