Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 24, 2026

Morphometric Analyses of Shape: The Analysis Software Toolbox for Craniofacial Shape Quantification in Zebrafish

Morphometric Analyses of Shape: The Analysis Software Toolbox for Craniofacial Shape Quantification in Zebrafish

Published on: February 27, 2026

What shape are dolphins? Building 3D morphable models from 2D images.

Thomas J Cashman¹, Andrew W Fitzgibbon

¹Faculty of Informatics, University of Lugano, Via Giuseppe Buffi 13, CH-6904 Lugano, Switzerland. thomas.cashman@usi.ch

IEEE Transactions on Pattern Analysis and Machine Intelligence

|March 7, 2012

Summary

Generating 3D morphable models from 2D images is now feasible with minimal user input. This method bypasses the need for costly 3D scans, enabling 3D model creation for diverse object classes.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

No single, stable 3D representation can explain pointing biases in a spatial updating task.

Scientific reports·2019

Same author

Comparison of view-based and reconstruction-based models of human navigational strategy.

Journal of vision·2017

Same author

What Can Pictures Tell Us About Web Pages? Improving Document Search Using Images.

IEEE transactions on pattern analysis and machine intelligence·2015

Same author

Joint demosaicing and denoising via learned nonparametric random fields.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2014

Same author

Modelling human visual navigation using multi-view scene reconstruction.

Biological cybernetics·2013

Same author

An automated calibration method for non-see-through head mounted displays.

Journal of neuroscience methods·2011

Area of Science:

Computer Vision
3D Computer Graphics
Machine Learning

Background:

3D morphable models (3DMMs) are essential for associating 3D geometry with 2D images.
Current 3DMM generation relies on 3D scans, which are infeasible for general object classes like animals.
Existing methods face economic and practical limitations.

Purpose of the Study:

To develop a method for generating 3D morphable models from 2D images.
To overcome the limitations of 3D scan-based 3DMM generation.
To enable 3D model creation for object classes without extensive 3D scan data.

Main Methods:

Utilizes a small amount of user interaction on 2D image collections.
Employs a linear combination of subdivision surfaces for model representation.

More Related Videos

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Related Experiment Videos

Last Updated: May 24, 2026

Morphometric Analyses of Shape: The Analysis Software Toolbox for Craniofacial Shape Quantification in Zebrafish

Morphometric Analyses of Shape: The Analysis Software Toolbox for Craniofacial Shape Quantification in Zebrafish

Published on: February 27, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Applies a novel combined continuous-discrete optimization strategy to fit silhouettes and key points.

Main Results:

Successfully generates 3D morphable models from 2D images, even without surface texture.
Demonstrates high-quality model generation for several natural object classes.
Validates the feasibility of the approach for non-strongly articulated objects.

Conclusions:

A cost-effective and practical method for 3D morphable model generation from 2D images has been established.
The approach requires minimal user input and a rough initial rigid model.
This technique significantly expands the applicability of 3D morphable models to new object categories.