Ghum & ghuml: Generative 3d human shape and articulated pose models

H Xu, EG Bazavan, A Zanfir… - Proceedings of the …, 2020 - openaccess.thecvf.com
We present a statistical, articulated 3D human shape modeling pipeline, within a fully
trainable, modular, deep learning framework. Given high-resolution complete 3D body …

Generative adversarial networks and their application to 3D face generation: A survey

M Toshpulatov, W Lee, S Lee - Image and vision computing, 2021 - Elsevier
Generative adversarial networks (GANs) have been extensively studied in recent years and
have been used to address several problems in the fields of image generation and computer …

Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering

S Yao, RZ Zhong, Y Yan, G Zhai, X Yang - arXiv preprint arXiv:2201.00791, 2022 - arxiv.org
While recent advances in deep neural networks have made it possible to render high-quality
images, generating photo-realistic and personalized talking head remains challenging. With …

H3d-net: Few-shot high-fidelity 3d head reconstruction

E Ramon, G Triginer, J Escur… - Proceedings of the …, 2021 - openaccess.thecvf.com
Recent learning approaches that implicitly represent surface geometry using coordinate-
based neural representations have shown impressive results in the problem of multi-view …

i3dmm: Deep implicit 3d morphable model of human heads

T Yenamandra, A Tewari, F Bernard… - Proceedings of the …, 2021 - openaccess.thecvf.com
We present the first deep implicit 3D morphable model (i3DMM) of full heads. Unlike earlier
morphable face models it not only captures identity-specific geometry, texture, and …

Npms: Neural parametric models for 3d deformable shapes

P Palafox, A Božič, J Thies… - Proceedings of the …, 2021 - openaccess.thecvf.com
Parametric 3D models have enabled a wide variety of tasks in computer graphics and vision,
such as modeling human bodies, faces, and hands. However, the construction of these …

Learning neural parametric head models

S Giebenhain, T Kirschstein… - Proceedings of the …, 2023 - openaccess.thecvf.com
We propose a novel 3D morphable model for complete human heads based on hybrid
neural fields. At the core of our model lies a neural parametric representation that …

AvatarMe: Realistically Renderable 3D Facial Reconstruction" in-the-wild"

A Lattas, S Moschoglou, B Gecer… - Proceedings of the …, 2020 - openaccess.thecvf.com
Over the last years, with the advent of Generative Adversarial Networks (GANs), many face
analysis tasks have accomplished astounding performance, with applications including, but …

3d morphable face models—past, present, and future

B Egger, WAP Smith, A Tewari, S Wuhrer… - ACM Transactions on …, 2020 - dl.acm.org
In this article, we provide a detailed survey of 3D Morphable Face Models over the 20 years
since they were first proposed. The challenges in building and applying these models …

Fitme: Deep photorealistic 3d morphable model avatars

A Lattas, S Moschoglou, S Ploumpis… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this paper, we introduce FitMe, a facial reflectance model and a differentiable rendering
optimization pipeline, that can be used to acquire high-fidelity renderable human avatars …