Naslov
Linear Regression vs. Deep Learning: A Simple Yet Effective Baseline for Human Body Measurement

Autori
Bartol, Kristijan ; Bojanić, David ; Petković, Tomislav ; Peharec, Stanislav ; Pribanić, Tomislav

Izvornik
Sensors (1424-8220) 22 (2022), 5; 1-19

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
body measurement ; linear regression ; statistical models ; anthropometry ; SMPL ; shape estimation ; mesh regression ; virtual try-on

Sažetak
We propose a linear regression model for the estimation of human body measurements. The input to the model only consists of the information that a person can self-estimate, such as height and weight. We evaluate our model against the state- of-the-art approaches for body measurement from point clouds and images, demonstrate the comparable performance with the best methods, and even outperform several deep learning models on public datasets. The simplicity of the proposed regression model makes it perfectly suitable as a baseline in addition to the convenience for applications such as the virtual try-on. To improve the repeatability of the results of our baseline and the competing methods, we provide guidelines toward standardized body measurement estimation.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA