Single depth image 3D face reconstruction via domain adaptive learning

doi:10.1007/s11704-023-3541-7

Front. Comput. Sci.

2024, Vol. 18

Issue (1) : 181342 https://doi.org/10.1007/s11704-023-3541-7

Artificial Intelligence

Single depth image 3D face reconstruction via domain adaptive learning

Xiaoxu CAI^1,²(

), Jianwen LOU¹(

), Jiajun BU¹, Junyu DONG³, Haishuai WANG¹, Hui YU²

¹. College of Computer Science and Technology, Zhejiang University, Hangzhou 310013, China
². School of Creative Technologies, University of Portsmouth, Portsmouth PO1 2DJ, UK
³. College of Computer Science and Technology, Ocean University of China, Qingdao 266100, China

Download: PDF(1600 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Corresponding Author(s): Xiaoxu CAI,Jianwen LOU

Just Accepted Date: 14 November 2023 Issue Date: 08 January 2024

Cite this article:

Xiaoxu CAI,Jianwen LOU,Jiajun BU, et al. Single depth image 3D face reconstruction via domain adaptive learning[J]. Front. Comput. Sci., 2024, 18(1): 181342.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-023-3541-7
https://academic.hep.com.cn/fcs/EN/Y2024/V18/I1/181342

Fig.1 The main pipeline of the proposed 3D face reconstruction method

Fig.2 Comparison with the state-of-the-art depth-based method, FDR. The results of FDR are furnished by its authors. RGB images serve solely as visual references here and are not used as inputs in the reconstruction algorithm

Fig.3 Comparison with leading RGB-based methods: D3DFR, 3DDFA2, MICA, and HRN. Notably, our approach did not employ RGB images as input

Tab.1 Head pose estimation errors on Biwi dataset. Here are the top three results highlighted in red, green, and blue, respectively

1	Zhong Y, Pei Y, Li P, Guo Y, Ma G, Liu M, Bai W, Wu W, Zha H. Face denoising and 3D reconstruction from a single depth image. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition. 2020, 117–124
2	Deng Y, Yang J, Xu S, Chen D, Jia Y, Tong X. Accurate 3D face reconstruction with weakly-supervised learning: from single image to image set. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019, 285–295
3	Guo J, Zhu X, Yang Y, Yang F, Lei Z, Li S Z. Towards fast, accurate and stable 3D dense face alignment. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 152–168
4	Zielonka W, Bolkart T, Thies J. Towards metrical reconstruction of human faces. In: Proceedings of the 17th European Conference on Computer Vision. 2022, 250–269
5	Lei B, Ren J, Feng M, Cui M, Xie X. A hierarchical representation network for accurate and detailed face reconstruction from in-the-wild images. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023, 394–403
6	Cao Z, Chu Z, Liu D, Chen Y. A vector-based representation to enhance head pose estimation. In: Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision. 2021, 1187–1196
7	Meyer G P, Gupta S, Frosio I, Reddy D, Kautz J. Robust model-based 3D head pose estimation. In: Proceedings of IEEE International Conference on Computer Vision. 2015, 3649–3657
8	Borghi G, Venturelli M, Vezzani R, Cucchiara R. POSEidon: face-from-depth for driver pose estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2017, 5494–5503
9	Xin M, Mo S, Lin Y. EVA-GCN: head pose estimation based on graph convolutional networks. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021, 1462–1471

[1]	FCS-23541-OF-XC_suppl_1	Download
[2]	FCS-23541-OF-XC_suppl_2	Download

Viewed

Full text

Abstract

Cited

Shared

Discussed