Instant multi-view head capture through learnable registration

T Bolkart, T Li, MJ Black - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Existing methods for capturing datasets of 3D heads in dense semantic correspondence are
slow and commonly address the problem in two separate steps; multi-view stereo (MVS) …

Spectre: Visual speech-informed perceptual 3d facial expression reconstruction from videos

PP Filntisis, G Retsinas… - Proceedings of the …, 2023 - openaccess.thecvf.com
The recent state of the art on monocular 3D face reconstruction from image data has made
some impressive advancements, thanks to the advent of Deep Learning. However, it has …

Reinforced disentanglement for face swapping without skip connection

X Ren, X Chen, P Yao, HY Shum… - Proceedings of the …, 2023 - openaccess.thecvf.com
The SOTA face swap models still suffer the problem of either target identity (ie, shape) being
leaked or the target non-identity attributes (ie, background, hair) failing to be fully preserved …

3d-aware facial landmark detection via multi-view consistent training on synthetic data

L Zeng, L Chen, W Bao, Z Li, Y Xu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Accurate facial landmark detection on wild images plays an essential role in human-
computer interaction, entertainment, and medical applications. Existing approaches have …

Deep learning for head pose estimation: A survey

A Asperti, D Filippini - SN Computer Science, 2023 - Springer
Head pose estimation (HPE) is an active and popular area of research. Over the years,
many approaches have constantly been developed, leading to a progressive improvement …

Position: measure dataset diversity, don't just claim it

D Zhao, JTA Andrews, O Papakyriakopoulos… - arXiv preprint arXiv …, 2024 - arxiv.org
Machine learning (ML) datasets, often perceived as neutral, inherently encapsulate abstract
and disputed social constructs. Dataset curators frequently employ value-laden terms such …

Hairnerf: Geometry-aware image synthesis for hairstyle transfer

S Chang, G Kim, H Kim - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
We propose a novel hairstyle transferred image synthesis method considering the
underlying head geometry of two input images. In traditional GAN-based methods …

Visual speech-aware perceptual 3d facial expression reconstruction from videos

PP Filntisis, G Retsinas… - arXiv preprint arXiv …, 2022 - arxiv.org
The recent state of the art on monocular 3D face reconstruction from image data has made
some impressive advancements, thanks to the advent of Deep Learning. However, it has …

Hiface: High-fidelity 3d face reconstruction by learning static and dynamic details

Z Chai, T Zhang, T He, X Tan… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract 3D Morphable Models (3DMMs) demonstrate great potential for reconstructing
faithful and animatable 3D facial surfaces from a single image. The facial surface is …

UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model

X Fan, J Li, Z Lin, W Xiao, L Yang - European Conference on Computer …, 2025 - Springer
Audio-driven 3D facial animation aims to map input audio to realistic facial motion. Despite
significant progress, limitations arise from inconsistent 3D annotations, restricting previous …