A framework for scene-flow driven creation of time-consistent dynamic 3D objects using mesh parametrizations

被引:0
|
作者
Klie, Patrick [1 ]
Okon, Eugen [1 ]
Stefanoski, Nikolce [1 ]
Ostermann, Joehn [1 ]
机构
[1] Leibniz Univ Hannover, Inst Informat Verarbeitung, D-30167 Hannover, Germany
来源
关键词
3d motion analysis and tracking; surface modeling for 3-D scenes; multi-view image and 3D data processing; 3D mesh representation; 3D motion animation;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper we propose a novel method to create dynamic mesh sequences with fixed connectivity from multiple camera video streams. Fixed connectivity is useful for dynamic mesh coding as mesh connectivity has to be transmitted only once and not frame-wise. The proposed method runs automatically. It deploys mesh parametrizations and voronoi diagrams from the computer graphics realm as well as 2D optical and 3D scene flow from computer vision. Assuming that a given dynamic mesh sequence does not necessarily have constant connectivity, motion estimation is performed by applying a 3D motion field to a static reconstruction in one frame. Afterwards, mesh connectivity is transferred patch-wise from one frame to the next one using remeshing techniques. The entire method is independent of static mesh resolution, hence supplying a basis for dynamic mesh coding and simplification.
引用
收藏
页码:233 / 236
页数:4
相关论文
共 50 条
  • [1] Scalable linear predictive coding of time-consistent 3D mesh sequences
    Stefanoski, Nikolce
    Liu, Xiaoliang
    Klie, Patrick
    Ostermann, Joern
    2007 3DTV CONFERENCE, 2007, : 253 - 256
  • [2] Layered predictive coding of time-consistent dynamic 3D meshes using a non-linear predictor
    Stefanoski, Nikolce
    Klie, Patrick
    Liu, Xiaoliang
    Ostermann, Joern
    2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, : 2361 - 2364
  • [3] 3D Scene Analysis Using UIMA Framework
    Yang, Yubin
    Wei, Wei
    Lu, Tong
    Gao, Yang
    Zhang, Yao
    Yang, Chunsheng
    NEXT-GENERATION APPLIED INTELLIGENCE, PROCEEDINGS, 2009, 5579 : 369 - +
  • [4] Basis Constrained 3D Scene Flow on a Dynamic Proxy
    Birkbeck, Neil
    Cobzas, Dana
    Jaegersand, Martin
    2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2011, : 1967 - 1974
  • [5] Computing similarity among 3D objects using dynamic time warping
    Angeles-Yreta, A
    Figueroa-Nazuno, J
    PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS AND APPLICATIONS, PROCEEDINGS, 2005, 3773 : 319 - 326
  • [6] Robust semi-regular mesh representation of 3D dynamic objects
    Yang, JH
    Kim, CS
    Lee, SU
    PROCEEDINGS OF THE 2003 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL II: COMMUNICATIONS-MULTIMEDIA SYSTEMS & APPLICATIONS, 2003, : 664 - 667
  • [7] A framework for 3D tracking of frontal dynamic objects in autonomous cars
    Lotfi, Faraz
    Taghirad, Hamid D.
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 183 (183)
  • [8] View-Consistent 3D Scene Flow Estimation over Multiple Frames
    Vogel, Christoph
    Roth, Stefan
    Schindler, Konrad
    COMPUTER VISION - ECCV 2014, PT IV, 2014, 8692 : 263 - 278
  • [9] 3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans
    Rosinol, Antoni
    Gupta, Arjun
    Abate, Marcus
    Shi, Jingnan
    Carlone, Luca
    ROBOTICS: SCIENCE AND SYSTEMS XVI, 2020,
  • [10] A Real-time Time-consistent 2D-to-3D Video Conversion System Using Color Histogram
    Zhang, Zhen
    Yin, Shouyi
    Liu, Leibo
    Wei, Shaojun
    IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2015, 61 (04) : 524 - 530