TY - GEN
T1 - Learning Distribution Independent Latent Representation for 3D Face Disentanglement
AU - Zhang, Zihui
AU - Yu, Cuican
AU - Li, Huibin
AU - Sun, Jian
AU - Liu, Feng
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11
Y1 - 2020/11
N2 - Learning disentangled 3D face shape representation is beneficial to face attribute transfer, generation and recognition, etc. In this paper, we propose a novel distribution independence-based method to learn to decompose 3D face shapes. Specifically, we design a variational auto-encoder with Graph Convolutional Network (GCN), namely Mesh-Encoder, to model the distributions of identity and expression representations via variational inference. To disentangle facial expression and identity, we eliminate correlation of the two distributions, and enforce them to be independent by adversarial training. Extensive experiments show that the proposed approach can achieve state-of-the-art results in 3D face shape decomposition and expression transfer. Though focusing on disentanglement, our method also achieves the reconstruction accuracies comparable to the state-of-the-art 3D face reconstruction methods.
AB - Learning disentangled 3D face shape representation is beneficial to face attribute transfer, generation and recognition, etc. In this paper, we propose a novel distribution independence-based method to learn to decompose 3D face shapes. Specifically, we design a variational auto-encoder with Graph Convolutional Network (GCN), namely Mesh-Encoder, to model the distributions of identity and expression representations via variational inference. To disentangle facial expression and identity, we eliminate correlation of the two distributions, and enforce them to be independent by adversarial training. Extensive experiments show that the proposed approach can achieve state-of-the-art results in 3D face shape decomposition and expression transfer. Though focusing on disentanglement, our method also achieves the reconstruction accuracies comparable to the state-of-the-art 3D face reconstruction methods.
UR - https://www.scopus.com/pages/publications/85101484374
U2 - 10.1109/3DV50981.2020.00095
DO - 10.1109/3DV50981.2020.00095
M3 - 会议稿件
AN - SCOPUS:85101484374
T3 - Proceedings - 2020 International Conference on 3D Vision, 3DV 2020
SP - 848
EP - 857
BT - Proceedings - 2020 International Conference on 3D Vision, 3DV 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th International Conference on 3D Vision, 3DV 2020
Y2 - 25 November 2020 through 28 November 2020
ER -