NDLI: Quantitative Assessment of the Accuracy of 3D Face Shape Reconstruction

Content Provider	IEEE Xplore Digital Library
Author	Amin, S.H. Gillies, D.F.
Copyright Year	2008
Description	Author affiliation: Dept. of Comput., Imperial Coll. London, London (Amin, S.H.; Gillies, D.F.)
Abstract	This paper addresses the question of the accuracy of reconstruction of 3D face surfaces from single 2D face images. Shape reconstruction from 2D face images is an approximation process, and quantitative analysis of reconstruction accuracy is essential in order to validate the results. Recently 3D synthesis techniques using morphable models have become quite popular, however, they have only been shown to reconstruct accurately in a qualitative fashion. Different methods vary in performance, and it is very difficult to compare them using just qualitative results. This paper evaluates a shape reconstruction algorithm, based on the well known analysis by synthesis approach, which works on single 2D images with unknown intrinsic camera parameters. The evaluation of the reconstructed models is carried out using a quantitative approach based on geometric similarity and a weighted eigen distance. The algorithm proposes the use of a texture mapped shape model. The shape model is created in advance from a representative set of 3D face surfaces. A dense correspondence, which is essential for encoding 3D shape information, is established using rigid and non-rigid registration. The reconstruction is carried out by optimising over the shape parameters with an objective function that minimises differences between the 2D image and the corresponding projection of the 3D image. The accuracy of reconstruction is improved by using an annealing based approach to overcome the problems of multiple local minima due to the non-convexity of the search space.
Starting Page	1
Ending Page	7
File Size	8463993
Page Count	7
File Format	PDF
ISBN	9781424427291
DOI	10.1109/BTAS.2008.4699385
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2008-09-29
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Algorithm design and analysis Surface reconstruction Solid modeling Image analysis Annealing Shape Reconstruction algorithms Cameras Encoding Image reconstruction
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Face recognition based on a 3D morphable model

Quantitative Analysis of 3D Face Reconstruction using Annealing based Approach

Reconstruction of 3D mannequin by two-dimensional photos

Efficient 3D visual hull reconstruction based on marching cube algorithm

Analysis of shape from shading algorithms for fast and realistic 3D face reconstruction APCCAS2002

3D Reconstruction of Indoor Environment Using the Kinect Sensor

Landmark-based model-free 3D face shape reconstruction from video sequences

Accurate and efficient reconstruction of 3D faces from stereo images

Structured light 3D face scanning system

Quantitative Assessment of the Accuracy of 3D Face Shape Reconstruction

Similar Documents

Face recognition based on a 3D morphable model

Quantitative Analysis of 3D Face Reconstruction using Annealing based Approach

Reconstruction of 3D mannequin by two-dimensional photos

Efficient 3D visual hull reconstruction based on marching cube algorithm

Analysis of shape from shading algorithms for fast and realistic 3D face reconstruction APCCAS2002

3D Reconstruction of Indoor Environment Using the Kinect Sensor

Landmark-based model-free 3D face shape reconstruction from video sequences

Accurate and efficient reconstruction of 3D faces from stereo images

Structured light 3D face scanning system

Quantitative Assessment of the Accuracy of 3D Face Shape Reconstruction