Optimal Step Nonrigid ICP Algorithms for Surface Registration

By Brian Amberg, Sami Romdhani, Thomas Vetter. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

869 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d14b52e7148fbe05aa9e188a159303f1742e15d5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Using Locally Corresponding CAD Models for Dense 3D Reconstructions from a Single Image (2017, methodology): “Creating graph To create the LDC graph, we exploit the non-rigid ICP algorithm [2] to find a matching point for each vertex.”
Learning a model of facial shape and expression from 4D scans (2017, methodology): “There have been many approaches for aligning static face scans [Amberg et al. 2007; Salazar et al. 2014] but few methods focus on 4D data (sequences of 3D meshes).”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, methodology): “In this work, we merge two popular face models with Nonrigid ICP [2] to construct our 3DMM.”
Multilinear Autoencoder for 3D Face Model Learning (2018, background): “[2, 18], which enables reconstruction errors between the output meshes and the input scans to be estimated in a consistent way.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “The robust point matching (RPM) algorithm (Gold et al. 1998) are proposed to overcome the ICP limitations; the soft assignment and deterministic annealing strategy are adopted, and the rigid transformation model is generalized to a non-rigid one by using the thin-plate spline [TPS-RPM (Chui and Rang”
Static and dynamic 3D facial expression recognition: A comprehensive survey (2012, methodology): “Non-rigid ICP [54] Able to handle variations in initial pose and occlusions well and gives dense correspondence.”
Blending liquids (2014, methodology): “Our work is closely related to the non-rigid ICP algorithms [Amberg et al. 2007; Li et al. 2009].”
Robust single-view geometry and motion reconstruction (2009, methodology): “Various methods make use of a template model to simplify correspondence estimation and provide a prior for geometry and topology reconstruction, often relying on a small set of manually specified correspondences [Blanz and Vetter 1999; Allen et al. 2003; Pauly et al. 2005; Amberg et al. 2007].”
A 3D Morphable Model Learnt from 10,000 Faces (2016, methodology): “[24] built the Basel Face Model (BFM) by using an optimal step Nonrigid Iterative Closest Point (NICP) algorithm [4] to directly align scans of 200 subjects with a template.”
Large Scale 3D Morphable Models (2017, methodology): “The method of Amberg et al. (2007) proposes an efﬁcient and accurate minimisation of the energy (4)—we invite the interested reader to explore this paper for more details.”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, methodology): “[34] defines a model: fðpiÞ 1⁄4 Aipi and uses stiffness to ensure adjacent transformations are similar.”
FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction (2020, methodology): “Then we use Non-rigid ICP[1] to register the standard template mesh to scanned mesh in neutral expression.”
Nonlinear 3D Face Morphable Model (2018, methodology): “Paysan et al. [26] use a Nonrigid Iterative Closest Point [3] to directly align 3D scans as an alternative to the UV space alignment method in [4].”
Morphable Face Models - An Open Framework (2017, methodology): “Algorithms, tailored for faces, such as [2], successfully deal with these domain specific issues.”