Correspondence distillation from nerf-based gan
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 …
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 …
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
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 …
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
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 …
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
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 …
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
Generating speech-driven 3D talking heads presents numerous challenges; among those is
dealing with varying mesh topologies. Existing methods require a registered setting, where …
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 …
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
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 …
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 …
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
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 …
suitable for shapes with extensive regions of missing data. Gaussian Processes are a …