Mesh representation matters:investigating the influence of different mesh features on perceptual and spatial fidelity of deep 3D morphable models  

作　　者：Robert KOSK Richard SOUTHERN Lihua YOU Shaojun BIAN Willem KOKKE Greg MAGUIRE 

机构地区：[1]Centre for Digital Entertainment,National Centre for Computer Animation,Bournemouth University,Poole BH125BB,UK [2]Humain Ltd.,Belfast BT12LA,UK [3]School of Creative and Digital Industries,Buckinghamshire New University,High Wycombe HP112JZ,UK [4]Belfast School of Art,Ulster University,Belfast BT151ED,UK

出　　处：《虚拟现实与智能硬件（中英文）》2024年第5期383-395,共13页Virtual Reality & Intelligent Hardware

基　　金：Supported by the Centre for Digital Entertainment at Bournemouth University by the UK Engineering and Physical Sciences Research Council(EPSRC)EP/L016540/1 and Humain Ltd.

摘　　要：Background Deep 3D morphable models(deep 3DMMs)play an essential role in computer vision.They are used in facial synthesis,compression,reconstruction and animation,avatar creation,virtual try-on,facial recognition systems and medical imaging.These applications require high spatial and perceptual quality of synthesised meshes.Despite their significance,these models have not been compared with different mesh representations and evaluated jointly with point-wise distance and perceptual metrics.Methods We compare the influence of different mesh representation features to various deep 3DMMs on spatial and perceptual fidelity of the reconstructed meshes.This paper proves the hypothesis that building deep 3DMMs from meshes represented with global representations leads to lower spatial reconstruction error measured with L_(1) and L_(2) norm metrics and underperforms on perceptual metrics.In contrast,using differential mesh representations which describe differential surface properties yields lower perceptual FMPD and DAME and higher spatial fidelity error.The influence of mesh feature normalisation and standardisation is also compared and analysed from perceptual and spatial fidelity perspectives.Results The results presented in this paper provide guidance in selecting mesh representations to build deep 3DMMs accordingly to spatial and perceptual quality objectives and propose combinations of mesh representations and deep 3DMMs which improve either perceptual or spatial fidelity of existing methods.

关 键 词：Shape modelling Deep 3D morphable models Representation learning Feature engineering Perceptual metrics 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]