VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment

P Tran, E Zakharov, LN Ho, AT Tran… - Proceedings of the …, 2024 - openaccess.thecvf.com
We present a 3D-aware one-shot head reenactment method based on a fully volumetric
neural disentanglement framework for source appearance and driver expressions. Our …

Gan-avatar: Controllable personalized gan-based human head avatar

B Kabadayi, W Zielonka, BL Bhatnagar… - … Conference on 3D …, 2024 - ieeexplore.ieee.org
Digital humans and, especially, 3D facial avatars have raised a lot of attention in the past
years, as they are the backbone of several applications like immersive telepresence in AR or …

Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes

Z Bai, F Tan, S Fanello, R Pandey… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract 3D head avatars built with neural implicit volumetric representations have achieved
unprecedented levels of photorealism. However the computational cost of these methods …

High-quality mesh blendshape generation from face videos via neural inverse rendering

X Ming, J Li, J Ling, L Zhang, F Xu - European Conference on Computer …, 2024 - Springer
Mesh-based facial blendshapes have been widely used in animation pipelines, while recent
advancements in neural geometry and appearance representations have enabled high …

PAV: Personalized Head Avatar from Unstructured Video Collection

A Caliskan, B Kicanaoglu, H Kim - European Conference on Computer …, 2024 - Springer
Abstract We propose PAV, Personalized Head Avatar for the synthesis of human faces
under arbitrary viewpoints and facial expressions. PAV introduces a method that learns a …

High-quality Animatable Eyelid Shapes from Lightweight Captures

J Lyu, F Xu - SIGGRAPH Asia 2024 Conference Papers, 2024 - dl.acm.org
High-quality eyelid reconstruction and animation are challenging for the subtle details and
complicated deformations. Previous works usually suffer from the trade-off between the …

VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence

P Tran, E Zakharov, LN Ho, L Hu, A Karmanov… - arxiv preprint arxiv …, 2024 - arxiv.org
We introduce VOODOO XP: a 3D-aware one-shot head reenactment method that can
generate highly expressive facial expressions from any input driver video and a single 2D …

Neural Parametric Human Hand Modeling with Point Cloud Representation

J Yang, W Quan, Z Shen, DM Yan, HY Wu - Proceedings of the 2024 …, 2024 - dl.acm.org
Recently, multi-layer perceptron-based implicit representations have achieved remarkable
successes in hand modeling. Compared with previous explicit mesh-based representation …

NeRFFaceSpeech: One-shot Audio-diven 3D Talking Head Synthesis via Generative Prior

G Kim, K Seo, S Cha, J Noh - arxiv preprint arxiv:2405.05749, 2024 - arxiv.org
Audio-driven talking head generation is advancing from 2D to 3D content. Notably, Neural
Radiance Field (NeRF) is in the spotlight as a means to synthesize high-quality 3D talking …

[PDF][PDF] GGAvatar: Dynamic Facial Geometric Adjustment for Gaussian Head Avatar

X Li, J Wang, Y Xuan, G Yao, Y Pan - 2024 - diglib7.eg.org
Reconstructing animatable 3D head avatars from target subject videos has long been a
significant challenge and a hot topic in computer graphics. This paper proposes GGAvatar, a …