3D-PSSIM: Projective Structural Similarity for 3D Mesh Quality Assessment Robust to Topological Irregularities

被引:0
作者
Lee, Seongmin [1 ]
Kang, Jiwoo [2 ]
Lee, Sanghoon [1 ]
Lin, Weisi [3 ]
Bovik, Alan Conrad [4 ]
机构
[1] Yonsei Univ, Dept Elect & Elect Engn, Seoul 03722, South Korea
[2] Sookmyung Womens Univ, Div Artificial Intelligence Engn, Seoul 04310, South Korea
[3] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore
[4] Univ Texas Austin, Dept Elect & Comp Engn, Lab Image & Video Engn, Austin, TX 78712 USA
基金
新加坡国家研究基金会;
关键词
3D mesh quality assessment; projective structural similarity; topology robust mesh quality assessment; POINT CLOUD QUALITY; VISUAL QUALITY; ERROR;
D O I
10.1109/TPAMI.2024.3422490
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Despite acceleration in the use of 3D meshes, it is difficult to find effective mesh quality assessment algorithms that can produce predictions highly correlated with human subjective opinions. Defining mesh quality features is challenging due to the irregular topology of meshes, which are defined on vertices and triangles. To address this, we propose a novel 3D projective structural similarity index (3D-PSSIM) for meshes that is robust to differences in mesh topology. We address topological differences between meshes by introducing multi-view and multi-layer projections that can densely represent the mesh textures and geometrical shapes irrespective of mesh topology. It also addresses occlusion problems that occur during projection. We propose visual sensitivity weights that capture the perceptual sensitivity to the degree of mesh surface curvature. 3D-PSSIM computes perceptual quality predictions by aggregating quality-aware features that are computed in multiple projective spaces onto the mesh domain, rather than on 2D spaces. This allows 3D-PSSIM to determine which parts of a mesh surface are distorted by geometric or color impairments. Experimental results show that 3D-PSSIM can predict mesh quality with high correlation against human subjective judgments, across the presence of noise, even when there are large topological differences, outperforming existing mesh quality assessment models.
引用
收藏
页码:9595 / 9611
页数:17
相关论文
共 80 条
[31]   Fully Deep Blind Image Quality Predictor [J].
Kim, Jongyoo ;
Lee, Sanghoon .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2017, 11 (01) :206-220
[32]  
Kim SJ, 2002, 10TH PACIFIC CONFERENCE ON COMPUTER GRAPHICS AND APPLICATIONS, PROCEEDINGS, P276, DOI 10.1109/PCCGA.2002.1167871
[33]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[34]   Perceptually driven 3D distance metrics with application to watermarking [J].
Lavoue, Guillaume ;
Gelasca, Elisa Drelie ;
Dupont, Florent ;
Baskurt, Atilla ;
Ebrahimi, Touradj .
APPLICATIONS OF DIGITAL IMAGE PROCESSING XXIX, 2006, 6312
[35]   On the Efficiency of Image Metrics for Evaluating the Visual Quality of 3D Models [J].
Lavoue, Guillaume ;
Larabi, Mohamed Chaker ;
Vasa, Libor .
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2016, 22 (08) :1987-1999
[36]   A Multiscale Metric for 3D Mesh Visual Quality Assessment [J].
Lavoue, Guillaume .
COMPUTER GRAPHICS FORUM, 2011, 30 (05) :1427-1437
[37]   Mesh saliency [J].
Lee, CH ;
Varshney, A ;
Jacobs, DW .
ACM TRANSACTIONS ON GRAPHICS, 2005, 24 (03) :659-666
[38]   CONTRAST MASKING IN HUMAN-VISION [J].
LEGGE, GE ;
FOLEY, JM .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA, 1980, 70 (12) :1458-1471
[39]   Sparse Graph Regularized Mesh Color Edit Propagation [J].
Li, Bo ;
Lai, Yu-Kun ;
Rosin, Paul L. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 :5408-5419
[40]   Visual Saliency and Quality Evaluation for 3D Point Clouds and Meshes: An Overview [J].
Lin, Weisi ;
Lee, Sanghoon .
APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING, 2022, 11 (01)