A Survey of Non-Rigid 3D Registration

Deng, Bailin; Yao, Yuxin; Dyke, Roberto M.; Zhang, Jie

doi:10.48550/arxiv.2203.07858

Cited by 3 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the 3D face point clouds on the source and the target face, the point cloud registration can be defined as aligning a source point cloud to a target point cloud. The point cloud registration can be grouped into three broad categories [28] namely 1) Deformation Field, 2) Extrinsic Methods and 3) Learning-based methods. Deformation Field-based techniques could be defined as the computation of deformation between the two-point clouds, which can be achieved either by assuming pointwise position [29] variables or by pointwise affine transformations [30].…”

Section: Proposed Methodsmentioning

confidence: 99%

“…However, the use of existing point cloud registration for this precise application of 3D face morphing point cloud generation will pose challenges such as: registration using the same individual: Point cloud registration has mainly focused on the non-rigid registration of two-point clouds from the same individual [28]. This is primarily because high-quality registration aims to produce a globally consistent 3D mesh.…”

Section: Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

3-D Face Morphing Attacks: Generation, Vulnerability and Detection

Singh,

Ramachandra

2024

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Face Recognition systems (FRS) have been found vulnerable to morphing attacks, where the morphed face image is generated by blending the face images from contributory data subjects. This work presents a novel direction toward generating face-morphing attacks in 3D. To this extent, we have introduced a novel approach based on blending the 3D face point clouds corresponding to the contributory data subjects. The proposed method will generate the 3D face morphing by projecting the input 3D face point clouds to depth maps and 2D color images, followed by the image blending and wrapping operations performed independently on the color images and depth maps. We then back-project the 2D morphing color map and the depth map to the point cloud using the canonical (fixed) view. Given that the generated 3D face morphing models will result in holes due to a single canonical view, we have proposed a new algorithm for hole filling that will result in a high-quality 3D face morphing model. Extensive experiments are carried out on the newly generated 3D face dataset comprised of 675 3D scans corresponding to 41 unique data subjects and the publicly available Facescape database with 100 unique identities. Experiments are performed to benchmark the vulnerability of the proposed 3D morph generation scheme against automatic 2D, 3D FRS and human observer analysis. We also present the quantitative assessment of the quality of the generated 3D face morphing models using eight different quality metrics. Finally, we have proposed three different 3D face Morphing Attack Detection (3D-MAD) algorithms to benchmark the performance of the 3D face morphing attack detection techniques.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Proposed Methodsmentioning

confidence: 99%

3-D Face Morphing Attacks: Generation, Vulnerability and Detection

Singh,

Ramachandra

2024

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

show abstract

“…In this section, we briefly review the previous works of shape matching, commonly used map evaluation metrics, and various map solvers, that are most related to this work. We refer to recent surveys [9,43,4] for more thorough discussions of shape matching.…”

Section: Related Workmentioning

confidence: 99%

“…Shape correspondence is a fundamental task in Geometry Processing, acting as a building block for many downstream applications [46,43,9]. One of the key challenges in designing a successful general-purpose shape matching method is the choice of the objective function that should promote high quality correspondences and, at the same time, be easy enough to optimize in order to be applicable on complex, densely sampled geometric objects.…”

Section: Introductionmentioning

confidence: 99%

Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy Optimization

Magnet

Ren

Sorkine‐Hornung

et al. 2022

2022 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

We introduce pointwise map smoothness via the Dirichlet energy into the functional map pipeline, and propose an algorithm for optimizing it efficiently, which leads to highquality results in challenging settings. Specifically, we first formulate the Dirichlet energy of the pulled-back shape coordinates, as a way to evaluate smoothness of a pointwise map across discrete surfaces. We then extend the recently proposed discrete solver and show how a strategy based on auxiliary variable reformulation allows us to optimize pointwise map smoothness alongside desirable functional map properties such as bijectivity. This leads to an efficient map refinement strategy that simultaneously improves functional and point-to-point correspondences, obtaining smooth maps even on non-isometric shape pairs. Moreover, we demonstrate that several previously proposed methods for computing smooth maps can be reformulated as variants of our approach, which allows us to compare different formulations in a consistent framework. Finally, we compare these methods both on existing benchmarks and on a new rich dataset that we introduce, which contains non-rigid, non-isometric shape pairs with inter-category and crosscategory correspondences. Our work leads to a general framework for optimizing and analyzing map smoothness both conceptually and in challenging practical settings.

show abstract

“…In this work, we focus on computing correspondences between non-rigid shapes. This is a long-standing problem in Geometry Processing and related fields, with a wide range of techniques developed in the past few years [DYDZ22,Sah20]. A notable line of work in this domain uses the so-called functional map framework, which is based on manipulating correspondences as matrices in a reduced basis [OBS * 12].…”

Section: Introductionmentioning

confidence: 99%

Scalable and Efficient Functional Map Computations on Dense Meshes

Magnet

Ovsjanikov

2023

Computer Graphics Forum

View full text Add to dashboard Cite

We propose a new scalable version of the functional map pipeline that allows to efficiently compute correspondences between potentially very dense meshes. Unlike existing approaches that process dense meshes by relying on ad‐hoc mesh simplification, we establish an integrated end‐to‐end pipeline with theoretical approximation analysis. In particular, our method overcomes the computational burden of both computing the basis, as well the functional and pointwise correspondence computation by approximating the functional spaces and the functional map itself. Errors in the approximations are controlled by theoretical upper bounds assessing the range of applicability of our pipeline. With this construction in hand, we propose a scalable practical algorithm and demonstrate results on dense meshes, which approximate those obtained by standard functional map algorithms at the fraction of the computation time. Moreover, our approach outperforms the standard acceleration procedures by a large margin, leading to accurate results even in challenging cases.

show abstract

A Survey of Non-Rigid 3D Registration

Cited by 3 publications

References 49 publications

3-D Face Morphing Attacks: Generation, Vulnerability and Detection

3-D Face Morphing Attacks: Generation, Vulnerability and Detection

Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy Optimization

Scalable and Efficient Functional Map Computations on Dense Meshes

Contact Info

Product

Resources

About