Single image 3D reconstruction based on control point grid
Authors: 
Shujun Zhang, Wenxiao LiuAuthors Info & Claims
Pages 31875 - 31893
Abstract
In order to construct 3D meshes from a single image quickly and intuitively, this paper presents a 3D reconstruction method based on control point grid. The key idea is to calculate the 2D control point grid of the target area and elevate each control point according to a parameterized 3D growing rule proposed from prior knowledge. First, the contour of the target object is divided into a major component and side components and the skeleton of each component is extracted. 2D control point grid is calculated combining the curvature and geometric feature of the contour and lifted into 3D space with corresponding height defined by parameter mapping. Finally, a complete 3D model is obtained after component combination and texturing. Experimental results show that this method can reasonably and efficiently recover the 3D shape of the target object while maintaining fine curvature and geometric features.
References
[1]
Alsmirat MA, Jararweh Y, Ai-Ayyoub M et al (2017) Accelerating compute intensive medical imaging segmentation algorithms using hybrid CPU-GPU implementations. Multimed Tools Appl 76(3):3537---3555
[2]
Bo S, Xianjie Q, Zhaoqi W (2010) Survey of Shape from Image. J Com Res Dev 47(3):549---560
[3]
Buchanan P, Mukundan R, Doggett M (2013) Automatic single-view character model reconstruction. Proceedings of the International Symposium on Sketch-Based Interfaces and Modeling. ACM, pp 5---14
[4]
Changqing Z, Jianzhuang L (2012) Optimization-Based Precise Reconstruction of 3D Objects from Line Drawing. J Com CAD & CG 24(12):1585---1591
[5]
Chen T, Zhu Z, Shamir A et al (2013) 3-Sweep: extracting editable objects from a single photo. ACM Trans Graph (TOG) 32(6):2504---2507
[6]
Cook MT, Agah A (2009) A survey of sketch-based 3-D modeling techniques. Interact Comput 21(3):201---211
[7]
Criminisi A, Reid I, Zisserman A (2000) Single View Metrology. Int J Comput Vis 40(2):123---148
[8]
Eberly D (1998) Triangulation by ear clipping. Geometric Tools, LLC, Chapel Hill
[9]
Entem E, Barthe L, Cani MP et al (2015) Modeling 3D animals from a side-view sketch. Comput Graph 46:221---230
[10]
Grosse R, Johnson MK, Adelson EH, Freeman WT (2010) Ground truth dataset and baseline evaluations for intrinsic image algorithms. In: Proceedings of the International Conference on Computer Vision (ICCV), vol 30, no 2, pp 2335---2342
[11]
Hershberger J, Snoeyink J (1994) An O (n log n) implementation of the Douglas-Peucker algorithm for line simplification. Proceedings of the tenth annual symposium on Computational geometry. ACM, pp 383---384
[12]
Hoffman DD (1998) Visual Intelligence: How We Create What We See. W.W. Norton & Company, London
[13]
Huang Q, Wang H, Koltun V (2015) Single-view reconstruction via joint analysis of image and shape collections. ACM Trans Graph (TOG) 34(4):1---10
[14]
Ijiri T, Owada S, Igarashi T (2006) Seamless integration of initial sketching and subsequent detail editing in flower modeling. Comput Graph Forum. Blackwell Publishing, Inc 25(3):617---624
[15]
Kraevoy V, Sheffer A, van de Panne M (2009) Modeling from contour drawings. Proceedings of the 6th Eurographics Symposium on Sketch-Based interfaces and Modeling. ACM, pp 37---44
[16]
Mahmoud A-A, Shadi A, Yaser J et al (2018) Accelerating 3D medical volume segmentation using GPUs. Multimed Tools Appl 77(4):4939---4958
[17]
Olsen L et al (2009) Sketch-based modeling: A survey. Comput Graph 33(1):85---103
[18]
Oswald MR, Toppe E, Nieuwenhuis C et al (2011) A Survey on Geometry Recovery from a Single Image with Focus on Curved Object Reconstruction. Proceedings of the 2011 Conference on Innovations for Shape Analysis: Models and Algorithms. Dagstuhl Castle, Germany
[19]
Oswald MR, Toppe E, Cremers D (2012) Fast and Globally Optimal Single View Reconstruction of Curved Objects, CVPR, pp 534---541
[20]
Pebay P, Baker T (2001) A comparison of triangle quality measures. Proceedings to the 10th International Meshing Roundtable, Sandia National Laboratories, pp 327---340
[21]
Rother C, Kolmogorov V, Blake A (2004) Grabcut: interactive foreground extraction using iterated graph cuts. ACM Trans Graph (TOG) 23(3):309---314
[22]
Töppe E, Oswald MR, Cremers D, Rother C (2010) Image-based 3d modeling via cheeger sets. In Proc. Asian Conference on Computer Vision, Queenstown, New Zealand
[23]
Wither J et al (2009) Structure from silhouettes: a new paradigm for fast sketch-based design of trees. Comput Graph Forum 28(2):541---550
[24]
Xuejin C, Reality S (2008) Realistic Interpretation from Freehand Sketching. University of Science and Technology of China. Doctoral dissertation
[25]
Yongwei M, Feixia H, Xiaohong F et al (2015) Single Image Based 3D Symmetric Free-Form Objects Reconstruction. J Com CAD & CG 27(9):1637---1647
[26]
Zanni C, Bernhardt A, Quiblier M, Cani M-P (2013) SCALe-invariant Integral Surfaces. Comput Graph Forum 32(8):219---232
[27]
Zhang TY, Suen CY (1984) A fast parallel algorithm for thinning digital patterns. Commun ACM 27(3):236---239
[28]
Zou C, Peng X, Lv H, Chen S, Fu H, Liu J (2015) Sketch-based 3-D modeling for piecewise planar objects in single images. Comput Graph 46(C):130---137
- Single image 3D reconstruction based on control point grid
Recommendations
3D surface point and wireframe reconstruction from multiview photographic images
This paper describes a new method for reconstructing 3D surface points and a wireframe on the surface of a freeform object using a small number, e.g. 10, of 2D photographic images. The images are taken at different viewing directions by a perspective ...
TextureMe: High-Quality Textured Scene Reconstruction in Real Time
Three-dimensional (3D) reconstruction using an RGB-D camera has been widely adopted for realistic content creation. However, high-quality texture mapping onto the reconstructed geometry is often treated as an offline step that should run after geometric ...
Texture map generation for 3D reconstructed scenes
We present a novel method for generating texture maps for 3D geometric models reconstructed using consumer RGB-D sensors. Our method generates a texture map for a simplified 3D mesh of the reconstructed scene using spatially and temporally sub-sampled ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © Copyright © 2018 Springer Science+Business Media, LLC, part of Springer Nature.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 01 December 2018
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 29 Jan 2025