计算机科学 ›› 2020, Vol. 47 ›› Issue (11A): 271-275.doi: 10.11896/jsjkx.200400030

• 计算机图形学&多媒体 • 上一篇    下一篇

交互标记约束的三维网格序列分割

郑磊1, 吴俊威2, 林俊勉2, 潘翔2   

  1. 1 浙江广播电视集团 杭州 311200
    2 浙江工业大学计算机科学与技术学院 杭州 310023
  • 出版日期:2020-11-15 发布日期:2020-11-17
  • 通讯作者: 吴俊威(470720501@qq.com)
  • 作者简介:zl099@zrtg.com
  • 基金资助:
    浙江省自然科学基金(LY19F020031)

Marker-constrained Interactive Segmentation of 3D Animated Meshes

ZHENG Lei1, WU Jun-wei2, LIN Jun-mian2, PAN Xiang2   

  1. 1 Zhejiang Radio and Television Group,Hangzhou 311200,China
    2 College of Computer Science & Technology,Zhejiang University of Technology,Hangzhou 310023,China
  • Online:2020-11-15 Published:2020-11-17
  • About author:ZHENG Lei,born in 1976,senior engineer.His main research interests include system planning and design,technologyall media TV station design and integration of broadcasting technology and information.
    WU Jun-wei,born in 1995,is a member of China Computer Federation.His main research interests include compu-ter graphics and geometric processing.
  • Supported by:
    This work was supported by the Natural Science Foundation of Zhejiang Province,China (LY19F020031).

摘要: 已有交互分割只能适用于单一的三维模型,文中对已有算法进行了扩展,针对三维网格序列提出了交互标记约束分割算法。首先用户任意选择一个网格模型在分割线附近进行点交互,形成交互式分割的约束标记;然后,所提算法采用测地距离构造等距映射,建立其他帧和交互网格之间的映射关系,实现约束标记的自动传递;最后考虑分割边界所具有的凹特性和平滑性,根据约束标记定义局部邻域等值线对不同帧进行交互式分割。在实验部分,文中针对不同类型的三维网格序列进行分割性能分析。实验结果表明,所提算法在姿态变化下仍能够得到一致的分割效果,并且优于已有算法。

关键词: 标记传递, 等距映射, 点交互, 交互式分割, 三维网格序列

Abstract: Existing interactive approaches only works for single 3D meshes.In view of this,this paper proposes an interactive algorithm of segmenting 3D animated meshes based on 3D data correspondence.Firstly,users can mark some points on any one 3D mesh for interactive segmentation.Then,the algorithm can map users,marks to othermeshes by geodesic distance and isometric mapping.Finally,it performs interactive segmentation of other frames by transferred markers and iso-lines.Experimental results show that the algorithm can effectively segment different kinds of 3D animations.In addition,it can effectively improve the segmenting quality and is the exiting algorithms.

Key words: 3D animated meshes, Dot interaction, Interactive segmentation, Isometric mapping, Marker transfer

中图分类号: 

  • TP391
[1] FORSYTH D A,PONCE J.Computer vision:a modern ap-proach[M].Prentice Hall Professional Technical Reference,2002.
[2] ZHENG Q,SHARF A,TAGLIASACCHI A.Consensus skeleton for non-rigid space-time registration[J].Computer Graphics Forum,2010,29(2):635-644.
[3] KRAEVOY V,SHEFFERA.Cross-parameterization and compatible remeshing of 3D models[J].ACM Transactions on Graphics.2004,23(3):861-869.
[4] HAN L,CHENG Y.3D model retrieval method combining ske-leton structure and geometric details [J].Computer applications and software,2013,30(11):199-201.
[5] MANGAN A P,WHITAKER R T.Partitioning 3D surface meshes using watershed segmentation[J].IEEE Transactions on Visualization and Computer Graphics,1999,5(4):308-321.
[6] KATZ S,TAL A.Hierarchical Mesh Decomposition using Fuzzy Clustering and Cuts[J].ACM Transactions on Graphics,2003,22(3):954-961.
[7] SHAPIRA L,SHALOM S,SHAMIR A,et al.Contextual part analogies in 3D objects[J].International Journal of Computer Vision,2010,89(2/3):309-326.
[8] FANG Y,SUN M,KIM M,et al.Heat-mapping:A robust approach toward perceptually consistent mesh segmentation[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2011:2145-2152.
[9] SIDI O,VAN KAICK O,KLEIMANY,et al.Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering[M].ACM,2011.
[10] XIE X,FENG J.Volumetric shape contexts for mesh co-segmentation[J].Computer Aided Geometric Design,2016,43:159-171.
[11] SHU Z,QI C,XIN S,et al.Unsupervised 3D shape segmentation and co-segmentation via deep learning[J].Computer Aided Geometric Design,2016,43(C):39-52.
[12] ZHENG Y,TAI C L,AU O K C.Dot scissor:a single-click interface for mesh segmentation[J].IEEE Transactions onVisualization and Computer Graphics,2012,18(8):1304-1312.
[13] ZHENG Y,TAIC L.Mesh Decomposition with Cross-Boundary Brushes[C]//Computer Graphics Forum.Blackwell Publishing Ltd.2010,29(2):527-535.
[14] FAN L B,LIU L G,LIU K.Paint Mesh Cutting[J].Comput Graph Forum,2011,30(2):603-612.
[15] KALOGERAKIS E,HERTZMANN A,SINGH K.Learning 3D mesh segmentation and labeling[J].ACM Transactions on Graphics (TOG),2010,29(4):102:1-102:12.
[16] MARRAS S,BRONSTEIN M M,KAI H,et al.Motion-based mesh segmentation using augmented silhouettes[J].Graphical Models,2012,74(4):164-172.
[17] KAICK O V,FISH N,KLEIMAN Y,et al.Shape Segmentation by Approximate Convexity Analysis[J].Acm Transactions on Graphics,2014,34(1):1-11.
[18] CHEN X,GOLOVINSKIY A,FUNKHOUSER T A.A Benchmark for 3D Mesh Segmentation[J].Acm Transactions on Graphics,2009,28(3):341-352.
[1] 程志豪, 潘翔, 郑河荣.
时空约束下的三维动态模型一致性对应
Consistent Correspondence of 3D Dynamic Surface Based on Space-Time Constraints
计算机科学, 2019, 46(8): 303-309. https://doi.org/10.11896/j.issn.1002-137X.2019.08.050
[2] 张绍群.
基于紧集子覆盖的流形学习算法
Manifold Learning Algorithm Based on Compact Setsub-coverage
计算机科学, 2017, 44(Z6): 88-91. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.018
[3] 杨志才,裘杭萍,权冀川,雷智朋.
CPS拓扑结构节点重要性排序方法
Node Importance Ordering for Topology Structure of Cyber-physical Systems
计算机科学, 2015, 42(8): 128-131.
[4] .
流形学习方法中的若干问题分析

计算机科学, 2009, 36(4): 25-28.
[5] 党建武,杜晓刚,王阳萍.
基于配对堆的交互式医学图像分割算法的研究
Research of Interactive Medical Image Segmentation Algorithm Based on Paring Heap
计算机科学, 2009, 36(11): 290-292.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!