Contour-aware 3D reconstruction of side-view sketches

被引:6
|
作者
Ramos, Saulo [1 ]
Trevisan, Diogo Fernando [1 ]
Batagelo, Harlen C. [1 ]
Sousa, Mario Costa [2 ]
Gois, Joao Paulo [1 ]
机构
[1] Fed Univ ABC, Santo Andre, Brazil
[2] Univ Calgary, Calgary, AB, Canada
来源
COMPUTERS & GRAPHICS-UK | 2018年 / 77卷
基金
巴西圣保罗研究基金会;
关键词
Sketch-based modeling; Direct 3D reconstruction; HRBF implicits; Hermitian data; MODEL RECONSTRUCTION;
D O I
10.1016/j.cag.2018.09.009
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
The 3D reconstruction from a single 2D side-view sketch faces challenges in capturing details of the curves and inferring the hidden parts. Here, we introduce an approach that ensures the 2D contours are interpolated to a suitable 3D reconstruction while capturing the small details of the sketch. To this end, we propose a novel strategy that combines a proper 3D Hermitian data generation from the vicinity of the sketches with an approach for identification and completion of sketch curves. Feasible 3D models are then generated using Hermitian Radial Basis Functions (HRBF) Implicit Surfaces. Results indicate that our approach provides not only more detailed 3D reconstructed models but also more perceptual agreement from the input sketches in comparison to previous work. (C) 2018 Elsevier Ltd. All rights reserved.
引用
收藏
页码:97 / 107
页数:11
相关论文
共 50 条
  • [1] 3D Face Reconstruction from One Side-View Face Images
    Jo, Jaeik
    Jung, Yu Jin
    Kim, Jaihie
    [J]. 2014 International Conference on Electronics, Information and Communications (ICEIC), 2014,
  • [2] Modeling 3D animals from a side-view sketch
    Entem, Even
    Barthe, Loic
    Cani, Marie-Paule
    Cordier, Frederic
    van de Panne, Michiel
    [J]. COMPUTERS & GRAPHICS-UK, 2015, 46 : 221 - 230
  • [3] 3D-Aware Generative Model for Improved Side-View Image Synthesis
    Jo, Kyungmin
    Jin, Wonjoon
    Choo, Jaegul
    Lee, Hyunjoon
    Cho, Sunghyun
    [J]. 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 22805 - 22815
  • [4] Contour-aware network with class-wise convolutions for 3D abdominal multi-organ segmentation
    Gao, Hongjian
    Lyu, Mengyao
    Zhao, Xinyue
    Yang, Fan
    Bai, Xiangzhi
    [J]. MEDICAL IMAGE ANALYSIS, 2023, 87
  • [5] Single-view 3D Reconstruction Algorithm Based on View-aware
    Wang Nian
    Hu Xuyang
    Zhu Fan
    Tang Jun
    [J]. JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2020, 42 (12) : 3053 - 3060
  • [6] ESTIMATION OF 3D BODY SHAPE AND CLOTHING MEASUREMENTS FROM FRONTAL- AND SIDE-VIEW IMAGES
    Thota, Kundan Sai Prabhu
    Suh, Sungho
    Zhou, Bo
    Lukowicz, Paul
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, : 2631 - 2635
  • [7] 3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks
    Lun, Zhaoliang
    Gadelha, Matheus
    Kalogerakis, Evangelos
    Maji, Subhransu
    Wang, Rui
    [J]. PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2017, : 67 - 77
  • [8] Multi-view 3D reconstruction of seedling using 2D image contour
    Chen, Qingguang
    Huang, Shentao
    Liu, Shuang
    Zhong, Mingwei
    Zhang, Guohao
    Song, Liang
    Zhang, Xinghao
    Zhang, Jingcheng
    Wu, Kaihua
    Ye, Ziran
    Kong, Dedong
    [J]. BIOSYSTEMS ENGINEERING, 2024, 243 : 130 - 147
  • [9] Topologically-Aware Deformation Fields for Single-View 3D Reconstruction
    Duggal, Shivam
    Pathak, Deepak
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1526 - 1536
  • [10] A Semantically Aware Multi-View 3D Reconstruction Method for Urban Applications
    Wei, Rongke
    Pei, Haodong
    Wu, Dongjie
    Zeng, Changwen
    Ai, Xin
    Duan, Huixian
    [J]. APPLIED SCIENCES-BASEL, 2024, 14 (05):