Instant multi-view head capture through learnable registration
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) …
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 …
some impressive advancements, thanks to the advent of Deep Learning. However, it has …
Reinforced disentanglement for face swapping without skip connection
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 …
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
Accurate facial landmark detection on wild images plays an essential role in human-
computer interaction, entertainment, and medical applications. Existing approaches have …
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 …
many approaches have constantly been developed, leading to a progressive improvement …
Position: measure dataset diversity, don't just claim it
Machine learning (ML) datasets, often perceived as neutral, inherently encapsulate abstract
and disputed social constructs. Dataset curators frequently employ value-laden terms such …
and disputed social constructs. Dataset curators frequently employ value-laden terms such …
Hairnerf: Geometry-aware image synthesis for hairstyle transfer
We propose a novel hairstyle transferred image synthesis method considering the
underlying head geometry of two input images. In traditional GAN-based methods …
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 …
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
Abstract 3D Morphable Models (3DMMs) demonstrate great potential for reconstructing
faithful and animatable 3D facial surfaces from a single image. The facial surface is …
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 …
significant progress, limitations arise from inconsistent 3D annotations, restricting previous …