Generation of 3D human models and animations using simple sketches

Date

2020-01-01

Author

Akman, Alican
Sahillioğlu, Yusuf
Sezgin, T. Metin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

80
views

0
downloads

Generating 3D models from 2D images or sketches is a widely studied important problem in computer graphics. We describe the first method to generate a 3D human model from a single sketched stick figure. In contrast to the existing human modeling techniques, our method requires neither a statistical body shape model nor a rigged 3D character model. We exploit Variational Autoencoders to develop a novel framework capable of transitioning from a simple 2D stick figure sketch, to a corresponding 3D human model. Our network learns the mapping between the input sketch and the output 3D model. Furthermore, our model learns the embedding space around these models. We demonstrate that our network can generate not only 3D models, but also 3D animations through interpolation and extrapolation in the learned embedding space. Extensive experiments show that our model learns to generate reasonable 3D models and animations.

Subject Keywords

Computing methodologies, Computing methodologies, Learning latent representations, Neural networks

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85086005616&origin=inward
https://hdl.handle.net/11511/97207

Conference Name

Graphics Interface 2020, GI 2020

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Deep generation of 3D articulated models and animations from 2D stick figures Akman, Alican; Sahillioğlu, Yusuf; Sezgin, T. Metin (2022-12-01) Generating 3D models from 2D images or sketches is a widely studied important problem in computer graphics. We describe the first method to generate a 3D human model from a single sketched stick figure. In contrast to the existing human modeling techniques, our method does not require a statistical body shape model. We exploit Variational Autoencoders to develop a novel framework capable of transitioning from a simple 2D stick figure sketch, to a corresponding 3D human model. Our network learns the mapping ...
Comparison of regression techniques via Monte Carlo simulation Mutan, Oya Can; Ayhan, Hüseyin Öztaş; Department of Statistics (2004) The ordinary least squares (OLS) is one of the most widely used methods for modelling the functional relationship between variables. However, this estimation procedure counts on some assumptions and the violation of these assumptions may lead to nonrobust estimates. In this study, the simple linear regression model is investigated for conditions in which the distribution of the error terms is Generalised Logistic. Some robust and nonparametric methods such as modified maximum likelihood (MML), least absolut...
Efficient rendering of complex scenes on heterogeneous parallel architectures Yıldırım Kalkan, Gökçe; İşler, Veysi; Department of Computer Engineering (2014) In computer graphics, generating high-quality images at high frame rates for rendering complex scenes is a challenging task. A well-known approach to tackling this important task is to utilize parallel processing through distributing rendering and simulation tasks to different processing units. In this thesis, several methods of distributed rendering architectures are investigated, and the bottlenecks in distributed rendering are analyzed. Based on this analysis, guidelines for distributed rendering in a ne...
Steganography through perspective invariance Yaşaroğlu, Yağız; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2012) A novel approach for watermarking of 3D models is introduced, for which data is embedded into 3D models, whereas extracted from their projected 2D visual or 2D-plus-depth representations. Such a watermarking system is valuable, since most of the 3D content is being consumed as 2D visual data. Apart from the efficiency of embedding data into 3D models before generation of arbitrary 2D projections, in some use cases, such as free viewpoint video or computer games, 2D content has to be rendered at the client, ...
Photometric stereo considering highlights and shadows Büyükatalay, Soner; Halıcı, Uğur; Birgül, Özlem; Department of Electrical and Electronics Engineering (2011) Three dimensional (3D) shape reconstruction that aims to reconstruct 3D surface of objects using acquired images, is one of the main problems in computer vision. There are many applications of 3D shape reconstruction, from satellite imaging to material sciences, considering a continent on earth or microscopic surface properties of a material. One of these applications is the automated firearm identification that is an old, yet an unsolved problem in forensic science. Firearm evidence matching algorithms rel...

Citation Formats

A. Akman, Y. Sahillioğlu, and T. M. Sezgin, “Generation of 3D human models and animations using simple sketches,” Toronto, Virtual, Online, Kanada, 2020, vol. 2020-May, Accessed: 00, 2022. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85086005616&origin=inward.