High-Fidelity 3D Face Reconstruction from a Single Image via Gaussian Representation and Depth-Guided Refinement

Yudie Cai; Ruoling Qi; Yaqiu Zhang; Xi Chu

doi:10.54254/2755-2721/2025.PO25728

Article Information

Received: 17 July 2025

Published: 30 July 2025

DOI: https://doi.org/10.54254/2755-2721/2025.PO25728

Article Type: Research Article

Cite this article

Cai,Y.;Qi,R.;Zhang,Y.;Chu,X. (2025). High-Fidelity 3D Face Reconstruction from a Single Image via Gaussian Representation and Depth-Guided Refinement. Applied and Computational Engineering,178,139-149.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About this Volume

Volume Title: ACE Vol.178

Part of Series: Applied and Computational Engineering

ISSN: 2755-2721 (Print) / 2755-273X (Online)

Copyright & License

[1]Diao, H., Jiang, X., Fan, Y., Li, M. and Wu, H. (2024) 3D Face Reconstruction Based on a Single Image: A Review. IEEE Access.

[2]Kerbl, B., Kopanas, G., Leimkühler, T. and Drettakis, G. (2023) 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics, 42(4), 139–1.

[3]Zhao, Z., Bao, Z., Li, Q., Qiu, G. and Liu, K. (2024) PS-Avatar: A Point-Based Morphable Shape Model for Real-Time Head Avatar Creation with 3D Gaussian Splatting. arXiv preprint, arXiv: 2401.12900.

[4]Lan, Y., Tan, F., Qiu, D., Xu, Q., Genova, K., Huang, Z. et al. (2023) Gaussian3Diff: 3D Gaussian Diffusion for 3D Full Head Synthesis and Editing. arXiv preprint, arXiv: 2305.17119.

[5]Szymanowicz, S., Rupprecht, C. and Vedaldi, A. (2024) Splatter Image: Ultra-Fast Single-View 3D Reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10208–10217.

[6]Chan, E.R., Lin, C.Z., Nagano, M.A., Pan, B., De Mello, S. et al. (2022) Efficient Geometry-Aware 3D Generative Adversarial Networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16123–16133.

[7]Wang, X., Li, Y., Zhang, H. and Shan, Y. (2021) Towards Real-World Blind Face Restoration with Generative Facial Prior. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9168–9178.

[8]Bhat, S.F., Birkl, R., Wofk, D., Wonka, P. and Müller, M. (2023) ZoeDepth: Zero-Shot Transfer by Combining Relative and Metric Depth. arXiv preprint, arXiv: 2302.12288.

[9]Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V. et al. (2023) DINOv2: Learning Robust Visual Features without Supervision. arXiv preprint, arXiv: 2304.07193.

[10]Zhan, C., Zhang, Y., Lin, Y., Wang, G. and Wang, H. (2025) RDG-GS: Relative Depth Guidance with Gaussian Splatting for Real-Time Sparse-View 3D Rendering. arXiv preprint, arXiv: 2501.02568..

[11]Ko, J., Cho, K., Choi, D., Ryoo, K. and Kim, S. (2023) 3D GAN Inversion with Pose Optimization. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2967–2976.

[12]Yuan, Z., Zhu, Y., Li, Y., Liu, H. and Yuan, C. (2023) Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding. Proceedings of the IEEE/CVF International Conference on Computer Vision, 2437–2447.

[13]Xu, J. and Zhang, S. (2020) Status, Challenges, and Future Perspectives of Fringe Projection Profilometry. Optics and Lasers in Engineering, 135, 106193.

[14]Zeng, A., Song, S., Nießner, M., Fisher, M., Xiao, J. and Funkhouser, T. (2017) 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

[15]Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O. and Cohen-Or, D. (2021) Designing an Encoder for StyleGAN Image Manipulation. arXiv preprint, arXiv: 2102.02766.

[16]Richardson, E., Alaluf, Y., Patashnik, O., Nitzan, Y., Azar, Y., Shapiro, S. and Cohen-Or, D. (2021) Encoding in Style: A StyleGAN Encoder for Image-to-Image Translation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June.

[17]Alaluf, Y., Patashnik, O. and Cohen-Or, D. (2021) ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October.

[18]Roich, D., Mokady, R., Bermano, A.H. and Cohen-Or, D. (2021) Pivotal Tuning for Latent-Based Editing of Real Images. ACM Transactions on Graphics.

[19]Yin, Y., Zhang, Y., Wang, X., Wang, T., Li, X., Gong, Y., Fan, Y., Cun, X., Shan, Y., Oztireli, C., & Yang, Y. (2022). 3D GAN inversion with facial symmetry prior. arXiv preprint arXiv: 2211.16927.

[20]Bhattarai, A. R., Nießner, M., & Sevastopolsky, A. (2023). TriplaneNet: An encoder for EG3D inversion. arXiv preprint arXiv: 2303.13497.

[21]Yuan, Z., Zhu, Y., Li, Y., Liu, H., & Yuan, C. (2023). Make encoder great again in 3D GAN inversion through geometry and occlusion-aware encoding. arXiv preprint arXiv: 2303.12326.

[22]Chu, X., & Harada, T. (2024). Generalizable and animatable Gaussian head avatar. In *Proceedings of the Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)*.

[23]Kirschstein, T., Romero, J., Sevastopolsky, A., Nießner, M., & Saito, S. (2025). AVAT3R: Large animatable Gaussian reconstruction model for high-fidelity 3D head avatars. arXiv preprint arXiv: 2405.20717.

[24]Deng, Y., Wang, D., & Wang, B. (2024). Portrait4D-v2: Pseudo multi-view data creates better 4D head synthesizer. arXiv preprint arXiv: 2406.04494.