Correspondence distillation from nerf-based gan

Y Lan, CC Loy, B Dai - International Journal of Computer Vision, 2024 - Springer
The neural radiance field (NeRF) has shown promising results in preserving the fine details
of objects and scenes. However, unlike explicit shape representations eg, mesh, it remains …

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

Z Fan, S Peng, S **a - 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 …

A sparse and locally coherent morphable face model for dense semantic correspondence across heterogeneous 3D faces

C Ferrari, S Berretti, P Pala… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
The 3D Morphable Model (3DMM) is a powerful statistical tool for representing 3D face
shapes. To build a 3DMM, a training set of face scans in full point-to-point correspondence is …

A landmark-free approach for automatic, dense and robust correspondence of 3D faces

Z Fan, X Hu, C Chen, X Wang, S Peng - Pattern Recognition, 2023 - Elsevier
Global dense registration of 3D faces commonly prioritizes correspondences of facial
landmarks which are fiducial points for the anatomical structures. However, it is not always …

Probabilistic registration for Gaussian process three-dimensional shape modelling in the presence of extensive missing data

FM Valdeira, R Ferreira, A Micheletti, C Soares - SIAM Journal on …, 2023 - SIAM
We propose a shape fitting/registration method based on a Gaussian processes formulation,
suitable for shapes with extensive regions of missing data. Gaussian processes are a …

Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads

F Nocentini, T Besnier, C Ferrari, S Arguillere… - arxiv preprint arxiv …, 2024 - arxiv.org
Generating speech-driven 3D talking heads presents numerous challenges; among those is
dealing with varying mesh topologies. Existing methods require a registered setting, where …

Towards Fine-grained 3D Face Dense Registration: An Optimal Dividing and Diffusing Method

Z Fan, S Peng, S **a - arxiv preprint arxiv:2109.11204, 2021 - arxiv.org
Dense vertex-to-vertex correspondence between 3D faces is a fundamental and challenging
issue for 3D&2D face analysis. While the sparse landmarks have anatomically ground-truth …

Jointly Optimizing Expressional and Residual Models for 3D Facial Expression Removal

Q Zheng, Y Wang, Z Hu, X Zhang, Z Wu… - ACM Transactions on …, 2022 - dl.acm.org
This article proposes a facial expression removal method to recover a 3D neutral face from a
single 3D expressional or non-neutral face. We treat a 3D non-neutral face as the sum of its …

Expanding the generality of neural fields

Y Lan - 2025 - dr.ntu.edu.sg
Neural fields have emerged as a groundbreaking approach to representing 3D shapes,
garnering significant attention due to their compatibility with modern deep-learning …

Probabilistic Registration for Gaussian Process 3D shape modelling in the presence of extensive missing data

F Valdeira, R Ferreira, A Micheletti… - arxiv preprint arxiv …, 2022 - arxiv.org
We propose a shape fitting/registration method based on a Gaussian Processes formulation,
suitable for shapes with extensive regions of missing data. Gaussian Processes are a …