4.5 Article

Probabilistic Registration for Gaussian Process Three-Dimensional Shape Modelling in the Presence of Extensive Missing Data

Related references

Note: Only part of the references are listed.
Article Computer Science, Software Engineering

Sphere Face Model: A 3D morphable model with hypersphere manifold latent space using joint 2D/3D training

Diqiong Jiang et al.

Summary: 3D morphable models are generative models that represent face shape and appearance. However, traditional 3DMMs and identity embeddings have different distribution characteristics, leading to challenges in preserving fidelity and consistency in face reconstruction. To address this, the Sphere Face Model (SFM) is proposed, which uses a novel loss function and a two-stage training approach to ensure both fidelity and consistency.

COMPUTATIONAL VISUAL MEDIA (2023)

Article Computer Science, Artificial Intelligence

Towards a Complete 3D Morphable Model of the Human Head

Stylianos Ploumpis et al.

Summary: The study introduces the most complete 3DMM of the human head to date, which combines existing models of different overlapping head parts to achieve state-of-the-art performance. The new model builds a combined face-and-head shape model that blends the variability and facial detail of an existing face model with the full head modelling capability of an existing head model.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Robotics

Generalized Coherent Point Drift With Multi-Variate Gaussian Distribution and Watson Distribution

Zhe Min et al.

Summary: This approach utilizes Gaussian and Watson distributions for modeling error distributions, formulates the PSR problem as a MLE problem solved under the EM framework, showing potential clinical value and significant performance improvement.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Computer Science, Artificial Intelligence

A Bayesian Formulation of Coherent Point Drift

Osamu Hirose

Summary: By formulating coherent point drift in a Bayesian setting, the algorithm now guarantees convergence through variational Bayesian inference, provides a basis for interpreting parameters with the motion coherence definition as a prior distribution, and allows for both rigid and non-rigid registration in a single algorithm, enhancing robustness against target rotation. Additionally, an acceleration scheme has been proposed that can be applied to non-Gaussian kernels, providing greater efficiency than traditional coherent point drift.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Computer Science, Information Systems

From Noisy Point Clouds to Complete Ear Shapes: Unsupervised Pipeline

Filipa Valdeira et al.

Summary: Ears are a challenging region to model on the human face due to non-rigid deformations and difficulties in processing the data. The proposed pipeline aims to handle unordered 3D point clouds with issues such as occlusions and outliers, ultimately producing a dataset with completed missing data. Comparisons of registration and shape completion methods are provided to determine the best choices for each step.

IEEE ACCESS (2021)

Article Computer Science, Software Engineering

Recent advances in shape correspondence

Yusuf Sahillioglu

VISUAL COMPUTER (2020)

Article Computer Science, Artificial Intelligence

Gaussian Process Morphable Models

Marcel Luthi et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

Article Automation & Control Systems

Nonrigid Point Set Registration by Preserving Local Connectivity

Lifei Bai et al.

IEEE TRANSACTIONS ON CYBERNETICS (2018)

Review Statistics & Probability

Variational Inference: A Review for Statisticians

David M. Blei et al.

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION (2017)

Review Computer Science, Information Systems

Recent developments and trends in point set registration methods

Baraka Maiseli et al.

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION (2017)

Article Computer Science, Artificial Intelligence

Shape-aware surface reconstruction from sparse 3D point-clouds

Florian Bernard et al.

MEDICAL IMAGE ANALYSIS (2017)

Article Computer Science, Artificial Intelligence

Non-Rigid Point Set Registration by Preserving Global and Local Structures

Jiayi Ma et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2016)

Review Surgery

Three dimensional (3D) modelling and surgical planning in trauma and orthopaedics

Patrick Eniola Fadero et al.

SURGEON-JOURNAL OF THE ROYAL COLLEGES OF SURGEONS OF EDINBURGH AND IRELAND (2014)

Article Computer Science, Artificial Intelligence

Point Set Registration: Coherent Point Drift

Andriy Myronenko et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2010)

Review Computer Science, Artificial Intelligence

Statistical shape models for 3D medical image segmentation: A review

Tobias Heimann et al.

MEDICAL IMAGE ANALYSIS (2009)

Article Computer Science, Artificial Intelligence

On learning vector-valued functions

CA Micchelli et al.

NEURAL COMPUTATION (2005)