3d-aware blending with generative nerfs

H Kim, G Lee, Y Choi, JH Kim… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Image blending aims to combine multiple images seamlessly. It remains challenging for
existing 2D-based methods, especially when input images are misaligned due to differences …

Sparse to dense dynamic 3d facial expression generation

N Otberdout, C Ferrari, M Daoudi… - Proceedings of the …, 2022 - openaccess.thecvf.com
In this paper, we propose a solution to the task of generating dynamic 3D facial expressions
from a neutral 3D face and an expression label. This involves solving two sub-problems:(i) …

Facetunegan: Face autoencoder for convolutional expression transfer using neural generative adversarial networks

N Olivier, K Baert, F Danieau, F Multon, Q Avril - Computers & Graphics, 2023 - Elsevier
In this paper, we present FaceTuneGAN, a new 3D face model representation decomposing
and encoding separately facial identity and facial expression. We propose a first adaptation …

Towards fine-grained optimal 3d face dense registration: An iterative dividing and diffusing method

Z Fan, S Peng, S Xia - International Journal of Computer Vision, 2023 - Springer
Dense vertex-to-vertex correspondence (ie registration) between 3D faces is a fundamental
and challenging issue for 3D &2D face analysis. While the sparse landmarks are definite …

Fc-4dfs: Frequency-controlled flexible 4d facial expression synthesizing

X Lu, C Zhuang, Z Lu, Y Wang, J Xiao - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
4D facial expression synthesizing is a critical problem in the fields of computer vision and
graphics. Current methods lack flexibility and smoothness when simulating the inter-frame …

Learning streamed attention network from descriptor images for cross-resolution 3D face recognition

JBC Neto, C Ferrari, AN Marana, S Berretti… - ACM Transactions on …, 2023 - dl.acm.org
In this article, we propose a hybrid framework for cross-resolution 3D face recognition which
utilizes a Streamed Attention Network (SAN) that combines handcrafted features with …

Are 3d face shapes expressive enough for recognising continuous emotions and action unit intensities?

MK Tellamekala, Ö Sümer, BW Schuller… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Recognising continuous emotions and action unit (AU) intensities from face videos, requires
a spatial and temporal understanding of expression dynamics. Existing works primarily rely …

The florence 4D facial expression dataset

F Principi, S Berretti, C Ferrari… - 2023 IEEE 17th …, 2023 - ieeexplore.ieee.org
Human facial expressions change dynamically, so their recognition/analysis should be
conducted by accounting for the temporal evolution of face deformations either in 2D or 3D …

Generating multiple 4d expression transitions by learning face landmark trajectories

N Otberdout, C Ferrari, M Daoudi… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
In this article, we address the problem of 4D facial expressions generation. This is usually
addressed by animating a neutral 3D face to reach an expression peak, and then get back to …

Action unit detection by learning the deformation coefficients of a 3d morphable model

L Ariano, C Ferrari, S Berretti, A Del Bimbo - Sensors, 2021 - mdpi.com
Facial Action Units (AUs) correspond to the deformation/contraction of individual facial
muscles or their combinations. As such, each AU affects just a small portion of the face, with …