MA-NeRF: Motion-Assisted Neural Radiance Fields for Face Synthesis from Sparse Images

被引:1
作者
Zhang, Weichen [1 ]
Zhou, Xiang [1 ]
Cao, YuKang [2 ]
Feng, WenSen [3 ]
Yuan, Chun [1 ]
机构
[1] Tsinghua Univ, Shenzhen Int Grad Sch, Shenzhen 518055, Peoples R China
[2] Univ Hong Kong, Hong Kong, Peoples R China
[3] Huawei Technol, CG & XR Dept, Shenzhen 518129, Peoples R China
来源
2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME | 2023年
基金
国家重点研发计划;
关键词
3DMM; NeRF; facial model; motion prior;
D O I
10.1109/ICME55011.2023.00302
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We address the problem of photorealistic 3D face avatar synthesis from sparse images. Existing Parametric models for face avatar reconstruction struggle to generate details that originate from inputs. Meanwhile, although current NeRF-based avatar methods provide promising results for novel view synthesis, they fail to generalize well for unseen expressions. We improve from NeRF and propose a novel framework that, by leveraging the parametric 3DMM models, can reconstruct a high-fidelity drivable face avatar and successfully handle the unseen expressions. At the core of our implementation are structured displacement feature and semantic-aware learning module. Our structured displacement feature will introduce the motion prior as an additional constraints and help perform better for unseen expressions, by constructing displacement volume. Besides, the semantic-aware learning incorporates multi-level prior, e.g., semantic embedding, learnable latent code, to lift the performance to a higher level. Thorough experiments have been doen both quantitatively and qualitatively to demonstrate the design of our framework, and our method achieves much better results than the current state-of-the-arts.
引用
收藏
页码:1757 / 1762
页数:6
相关论文
共 20 条
[1]   A morphable model for the synthesis of 3D faces [J].
Blanz, V ;
Vetter, T .
SIGGRAPH 99 CONFERENCE PROCEEDINGS, 1999, :187-194
[2]   Authentic Volumetric Avatars from a Phone Scan [J].
Cao, Chen ;
Simon, Tomas ;
Kim, Jin Kyu ;
Schwartz, Gabe ;
Zollhoefer, Michael ;
Saito, Shun-Suke ;
Lombardi, Stephen ;
Wei, Shih-En ;
Belko, Danielle ;
Yu, Shoou-, I ;
Sheikh, Yaser ;
Saragih, Jason .
ACM TRANSACTIONS ON GRAPHICS, 2022, 41 (04)
[3]   Learning an Animatable Detailed 3D Face Model from In-The-Wild Images [J].
Feng, Yao ;
Feng, Haiwen ;
Black, Michael J. ;
Bolkart, Timo .
ACM TRANSACTIONS ON GRAPHICS, 2021, 40 (04)
[4]   Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction [J].
Gafni, Guy ;
Thies, Justus ;
Zollhoefer, Michael ;
Niessner, Matthias .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :8645-8654
[5]   GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction [J].
Gecer, Baris ;
Ploumpis, Stylianos ;
Kotsia, Irene ;
Zafeiriou, Stefanos .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :1155-1164
[6]   3D Semantic Segmentation with Submanifold Sparse Convolutional Networks [J].
Graham, Benjamin ;
Engelcke, Martin ;
van der Maaten, Laurens .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :9224-9232
[7]   AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis [J].
Guo, Yudong ;
Chen, Keyu ;
Liang, Sen ;
Liu, Yong-Jin ;
Bao, Hujun ;
Zhang, Juyong .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :5764-5774
[8]  
Ke ZH, 2022, AAAI CONF ARTIF INTE, P1140
[9]  
Liu X, 2022, Arxiv, DOI arXiv:2201.07786
[10]   NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections [J].
Martin-Brualla, Ricardo ;
Radwan, Noha ;
Sajjadi, Mehdi S. M. ;
Barron, Jonathan T. ;
Dosovitskiy, Alexey ;
Duckworth, Daniel .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :7206-7215