P 2: a robust and rotationally invariant shape descriptor with applications to mesh saliency
Tóm tắt
This work presents a robust and rotationally invariant shape descriptor, namely perception pronouncement (called P
2), to mathematically model the eye fixations. P
2 takes two criteria – the local consideration of surface curvature and the global consideration of viewindependent visibility – into account. Differing from existing works that often computed the intrinsic surface property of visibility in imaging space, a novel approach is proposed to approximate the attribute in object space using Gauss map and Ray tracing. With the presented shape descriptor, mesh saliency detection, which refers to reasoning about which regions or points of a surface are important, is more sensible, especially when 3D models fall into two categories: (1) the models possess significant interior/exterior structures; (2) the models contain regions where the contrast in visibility is high. For the models that are out of the categories, saliencies achieved by our approach are comparable to or even better than those of state-of-the-art methods.
Tài liệu tham khảo
A Appel. The notion of quantitative invisibility and the machine rendering of solids, In: Proc ACM Nat Conf, 1967, 387–393.
G V Brummelen. Heavenly Mathematics: the Forgotten Art of Spherical Trigonometry, Princeton University Press, 2012.
S Belongie, J Malik, J Puzicha. Shape matching and object recognition using shape contexts, IEEE Trans Pattern Anal Mach Intell, 2002, 24(4): 509–522.
U Castellani, M Cristani, S Fantoni, V Murino. Sparse points matching by combining 3D mesh saliency with statistical descriptors, Comput Graph Forum, 2008, 27(2): 643–652.
X Chen, A Saparov, B Pang, T Funkhouser. Schelling points on 3D surface meshes, ACMTrans Graph, 2012, 31(4): 13–15.
D Dimitrov. Geometric applications of principal component analysis, Master’s thesis, Freie University, Berlin, 2008.
D DeCarlo, A Finkelstein, S Rusinkiewicz, A Santella. Suggestive contours for conveying shape, ACM Trans Graph, 2003, 22(3): 848–855.
T K Dey, K Li, C Luo, P Ranjan, I Safa, Y Wang. Persistent heat signature for pose-oblivious matching of incomplete models, Comput Graph Forum, 2010, 29(5): 1545–1554.
S Fleishman, I Drori, D Cohen-Or. Bilateral mesh denoising, In: Proc SIGGRAPH’ 03, 2003, 950–953.
M Feixas, M Sbert, F González. A unified information-theoretic framework for viewpoint selection and mesh saliency, ACM Trans Appl Percept, 2009, 6(1): 1–23.
J Gallier. Geometric Methods and Applications for Computer Science and Engineering, Springer, NY, 2000.
R Gal, D Cohen-Or. Salient geometric features for partial shape matching and similarity, ACM Trans Graph, 2006, 25(1): 130–150.
M Harrower, C A Brewer. Colorbrewer.org: An online tool for selecting colour schemes for maps, Cartograph J, 2003, 40(1): 27–37.
S Howlett, J Hamill, C O’Sullivan. Predicting and evaluating saliency for simplified polygonal models, ACM Trans Appl Percept, 2005, 2(3): 286–308.
A Hertzmann, D Zorin. Illustrating smooth surfaces, In: Proc SIGGRAPH’ 00, 2000, 517–526.
L Itti, C Koch, E Niebur. A model of saliency-based visual attention for rapid scene analysis, IEEE Trans Pattern Anal Mach Intell, 1998, 20(11): 1254–1259.
C Koch, T Poggio. Predicting the visual world: silence is golden, Nat Neurosci, 1999, 2: 9–10.
Y Kim, A Varshney, D W Jacobs, F Guimbretière. Mesh saliency and human eye fixations, ACM Trans Appl Percept, 2010, 7(2): 1–13.
G Leifman, E Shtrom, A Tal. Surface regions of interest for viewpoint selection, In: IEEE Comput Vis Pattern Recognition (CVPR), 2012, 414–421.
C H Lee, A Varshney, D W Jacobs. Mesh saliency, ACM Trans Graph, 2005, 24(3): 659–666.
S Manay, D Cremers, B W Hong, A J Yezzi, S Soatto. Integral invariants for shape matching, IEEE Trans Pattern Anal Mach Intell, 2006, 28(10): 1602–1618.
M Meyer, M Desbrun, P Schröder, A H Barr. Discrete differential-geometry operators for triangulated 2-manifolds, In: Visualization and Mathematics III, Math Vis, 2003, 35–57.
R McDonnell, M Larkin, B Hernández, I Rudomin, C O’Sullivan. Eye-catching crowds: Saliency based selective variation, ACM Trans Graph, 2009, 28(3): 341–352.
R J Renka. Stripack: Delaunay triangulation and Voronoi diagram on the surface of a sphere, ACM Trans Math Softw, 1997, 23(3): 416–434.
S Rusinkiewicz. Estimating curvatures and their derivatives on triangle meshes, In: Proc IEEE 2nd Internat Symp 3DPVT, 2004, 486–493.
J Revelles, C Ure˜na, M Lastra. An efficient parametric algorithm for octree traversal, JWSCG, 2000, 212–219.
P Shilane, T Funkhouser. Distinctive regions of 3D surfaces, ACM Trans Graph, 2007, 26(2), Article No 7.
R Song, Y Liu, R R Martin, P L Rosin. 3D point of interest detection via spectral irregularity diffusion, Vis Comput, 2013, 29(6-8): 695–705.
R Song, Y Liu, R R Martin, P L Rosin. Mesh saliency via spectral processing, ACM Trans Graph, 2014, 33(1): 57–76.
G Taubin. Estimating the tensor of curvature of a surface from a polyhedral approximation, In: Proc Internat Conf Comput Vis, 1995, 902–907.
P Tao, J Cao, S Li, X Liu, L Liu. Mesh saliency via ranking unsalient patches in a descriptor space, Comput Graph, 2015, 46(0): 264–274.
C Tomasi, R Manduchi. Bilateral filtering for gray and color images, In: Proc IEEE Internat Conf Comput Vis, 1998, 839–846.
J M Wolfe. Guided search 2.0 a revised model of visual search, Psychonomic Bull Rev, 1994, 1(2): 202–238.
S Wang, N Li, S Li, Z Luo, Z Su, H Qin. Multi-scale mesh saliency based on low-rank and sparse analysis in shape feature space, Comput Aided Geom Design, 2015, 35-36: 206–214.
J Wu, X Shen, W Zhu, L Liu. Mesh saliency with global rarity, Graph Models, 2013, 75(5): 255–264.
S Yoshizawa, A Belyaev, H P Seidel. Fast and robust detection of crest lines on meshes, In: Proc ACM ymp Solid Phys Model, 2005, 227–232.
F Zhang, B Du, L Zhang. Saliency-guided unsupervised feature learning for scene classification, IEEE Trans Geosci Remote Sensing, 2015, 53(4): 2175–2184.
E Zhang, G Turk. Visibility-guided simplification, In: Proc IEEE Visibility, 2002, 267–274.