第一人称视角地形轮廓草图的真实空间重建

曾升; 耿国华; 邹林波; 周明全

doi:doi:10.3788/ope.20202808.1861

光学精密工程, 2020, 28 (8): 1861, 网络出版: 2020-11-02

第一人称视角地形轮廓草图的真实空间重建

Real spatial terrain reconstruction of first person point-of-view sketches

论文大纲

曾升耿国华邹林波周明全

作者单位

西北大学信息科学与技术学院, 陕西西安 710127

小孔成像相对深度关系周向分形插值旋转映射 pinhole imaging relative depth relation circumferential fractal Interpolation rotation mapping

摘要

第一人称2D地形草图重建三维模型是具有挑战性的研究, 由于缺失一维信息, 多数研究都侧重于研究自由设计地形及提高真实感的地面纹理映射方法, 却并未涉及更符合普通用户手绘的目的并遵循摄影几何规律的真实空间位置重建, 本文提出手绘草图直接生成符合真实空间位置的三维模型生成方法。首先, 遵循二维草图既定的形状规律、视觉遮挡关系, 根据小孔成像规律构建相对深度关系; 然后, 通过采样不同深度层的轮廓数据点进行椭圆扩展来建立等高线图, 周向采样点的分形插值来计算地形单元; 接着通过旋转映射来实现空间地形单元的非刚性变形, 从而实现第一人称视角下同一轮廓不同三维模型的构建; 最后, 加入柏林噪声以添加三维地形细节展示的随机效果。实验结果表明: 在相同的二维草图透视下, 可以构建具有不同真实空间位置的三维地形模型, 与三种草图地形建模方法相比, 解决了真实空间位置重建的问题。本文提出的方法更符合用户的设计目的, 实现任意同一投影草图轮廓的三维地形真实空间重建, 得到多层遮挡地形草图的多种真实空间位置布局, 并能满足地形特征的展示, 弥合了艺术意图与数字建模之间的鸿沟。

Abstract

It is challenging to reconstruct 3D terrain modelsbased on sketches drawn in the first-person pointofview. Owing to the lack of one-dimensional information, most studies focus on terrain-independent design and texture mapping methods to improve the realism; however, the spatial location is not considered in such methods.To address this limitation, we propose a methodto generate 3D modelsthat conform tothe real space position. First,based on the established shape rules and visual occlusion relation, the relative depth relationship is determined according to the geometric rules derived from photographs; then, a contour map is established by sampling the contour data points of different depth layers for ellipse expansion.Furthermore, the fractal interpolation of circumferential sampling points is performed to calculate terrain units, and the non-rigid deformation of spatial terrain elements is realized via rotation mapping. Finally, Berlin noise is added to improve the random effect of the 3D terrain display. Experimental results show that for the same 2D sketch perspective, 3D terrain models corresponding todifferent real spatial locations can be constructed; in this regard, the proposed method is different from the other three methods.Furthermore, it solves the problem of real space location reconstruction. Our method is more suitable for expressing the intended design purpose of users.It realizes the 3D terrain real space reconstruction of any 2D sketch; moreover, it obtains a variety of real space layouts of multi-layer occlusion terrainsin addition to displayingthe terrain features,which bridges the gap between artistic intent and the actual result.

参考文献

[1] CHOY C.B, XU D, GWAK J, et al.. 3D-R2N2: A unified approach for single and multi-view 3D object reconstruction［C］. European Conference on Computer Vision, 2016.

[2] SAXENA A, SUN M, NG A Y. Make3D: Learning 3D scene structure from a single still image［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(5): 824-840.

[3] NIU C, LI J, XU K. Im2Struct: Recovering 3D shape structure from a single RGB image［C］. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 4521-4529.

[4] WU J, ZHANG C, ZHANG X, et al.. Learning shape priors for single-view 3D completion and reconstruction［C］.Computer Vision - ECCV, 2018: 673-691.

[5] WANG P S, SUN C Y, LIU Y, et al.. Adaptive O-CNN: A patch-based deep representation of 3D shapes［J］. ACM Trans. Graph. 2018, 37(6): 1-11.

[6] LIU C, YANG J, CEYLAN D, et al.. PlaneNet: Piece-wise planar reconstruction from a single RGB image［C］. CVPR, 2018.

[7] LI C, PAN H, LIU Y, et al.. BendSketch: Modeling freeform surfaces through 2D sketching［J］. Acm Transactions on Graphics, 2017, 36(4): 125.

[8] 杨洪波. CAD建模中的草图约束处理［J］. 光学精密工程, 1995, 3(6): 18-22.

YANG H B. Sketch constraint processing in CAD modeling［J］. Opt. Precision Eng., 1995, 3(6): 18-22.(in Chinese).

[9] EITZ M, HILDEBRAND K, BOUBEKEUR T, et al.. An evaluation of descriptors for large-scale image retrieval from sketched feature lines［J］. Computers and Graphics, 2010, 34(5): 482-498.

[10] VOSS R.F. Fractals in Nature: From Characterization to Simulation［M］. In: Peitgen HO., Saupe D. (eds) The Science of Fractal Images. Springer, 1988.

[11] ZHOU H, SUN J, TURK G, et al.. Terrain synthesis from digital elevation models［J］. IEEE Transactions on Visualization and Computer Graphics, 2007, 13(4): 834-848.

[12] 王莹,王延杰,周渝人,等. 基于注入式仿真平台的自适应真实感地形生成算法［J］. 光学精密工程, 2014, 22(12): 3419-3426.

WANG. Y, WANG Y J, ZHOU Y R, et al.. Real adaptive topography optimization algorithm based on injection simulation platform ［J］. Opt. Precision Eng., 2014, 22(12): 3419-3426.(in Chinese).

[13] RUSNELL B, MOULD D, ERAMIAN M G. Feature-rich distance-based terrain synthesis［J］. The Visual Computer, 2009, 25(5-7): 573-579.

[14] J E GAIN, P MARAIS, W STRA?ER. Terrain sketching［C］. The 2009 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, 2009.

[15] F P TASSE, J E GAIN, P MARAIS. Enhanced texture-based terrain synthesis on graphics hardware［J］. Computer Graphics Foru, 2012, 31(6): 1959-1972.

[16] F P TASSE, A EMILIEN, M P CANI, et al.. Feature-based terrain editing from complex sketches［J］. Computers & Graphics, 2014, 4: 101-115.

[17] V A D PASSOS, T IGARASHI. Landsketch: A first person point-of-view example-based terrain modeling approach［C］. In: International Symposium on Sketch-based Interfaces & Modeling, 2013.

[18] M ARIYAN, D. MOULD. Terrain synthesis using curve networks［C］. In: Graphics Interface Conference, 2015.

[19] K KETABCHI, A RUNIONS, F F SAMAVATI. 3D maquetter: Sketch-based 3D content modeling for digital earth［C］. In: International Conference on Cyberworlds, 2016: 415.

[20] M Becher, M Krone, G Reina, et al.. Feature-based volumetric terrain generation［J］. IEEE Transactions on Visualization and Computer Graphics, 2017, 8(99): 1-1.

[21] TALGORN, F. BELHADJ. Real-time sketch-based terrain generation［C］. Computer Graphics International, 2018: 13-18.

[22] 赵祚喜, 冯荣, 朱裕昌,等. 空间点的多视图DLT三维定位［J］. 光学精密工程, 2020, 28(1): 212-222.

ZHAO ZUO-XI, FENG RONG, ZHU YU-CHANG, et al.. Multi-view DLT three-dimensional positioning method for spatial points［J］. Opt. Precision Eng., 2020, 28(1): 212-222. (in Chinese).

[23] 李云雷, 张曦, 屠大维. 基于立体定向靶标的探针式多视场三维视觉测量系统［J］. 光学精密工程, 2019, 27(1): 34-44.

LI YUN-LEI, ZHANG XI, TU DA-WEI. Probe-based multi-view field 3D vision measurement system based on three-dimensional orientation target［J］. Opt. Precision Eng., 2019, 27(1): 34-44. (in Chinese).

[24] 于洋, 朴燕, 倪焱,等. 基于ROS与三维点云图像的室内物体精准定位［J］. 液晶与显示, 2019, 34(6): 598-604.

YU YANG, PIAO YAN, NI YAN, et al.. Precise location of indoor objects based on ROS and point cloud images［J］. Chinese Journal of Liquid Crystals and Displays, 2019, 34(6): 598-604. (in Chinese).

[25] 韩延祥张志胜戴敏. 用于目标测距的单目视觉测量方法［J］. 光学精密工程, 2011,19(5): 1110-1117.

HAN. Y X, ZHANG Z S, DAI M. Monocular vision system for distance measurement based on feature points［J］. Opt. Precision Eng., 2011, 19(5): 1110-1117 (in Chinese).

[26] GODARD, CLéMENT, MAC AODHA O, et al.. Unsupervised Monocular Depth Estimation with Left-Right Consistency［C］. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[27] CHU H, MA W C, URTASUN R, et al.. SurfConv: Bridging 3D and 2D Convolution for RGBD Images［C］. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

[28] BATTIATO S, CURTI S, CASCIA M L. Depth map generation by image classification［C］. Three-dimensional Image Capture & Applications VI. International Society for Optics and Photonics, 2004.

[29] HA H, IM S, PARK J, et al.. High-quality depth from uncalibrated small motion Clip［C］. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2016.

[30] 刘东生, 陈建林, 费点,等. 基于深度相机的大场景三维重建［J］. 光学精密工程, 2020, 28(1).: 234-243.

LIU DONG-SHENG, CHEN JIAN-LIN FEI DIAN, et al.. Three-dimensional reconstruction of large-scale scene based on depth camera［J］. Opt. Precision Eng., 2020, 28(1): 234-243. (in Chinese).

[31] ZHOU, PENGBO ,LI K, WEI W, et al.. Fast generation method of 3d scene in chinese landscape painting［J］. Multimedia Tools & Applications. doi: org/10.1007/s11042-019-7476-9.20. 2019.

[32] BLOOMENTHAL, JULES, ROKNE, et al.. Homogeneous coordinates［J］. Visual Computer, 425(1994) 15-26.

[33] 孙洪泉. 《分形几何与分形插值》［M］. 北京: 科学出版社, 2011.

SUN HONG-QUAN. Fractal Geometry and Fractal Interpolation［M］. Beijing: Science Press, 2011.(in Chinese).

[34] K PERLIN. Improving noise［J］. Acm Transactions on Graphics, 2002, 21 (3): 681-682.

[35] D MATTPHARR, N G HUMPHREYS. Physically based Rendering［M］. San Francisco: Morgan Kaufmann, 2010.

曾升, 耿国华, 邹林波, 周明全. 第一人称视角地形轮廓草图的真实空间重建[J]. 光学精密工程, 2020, 28(8): 1861. ZENG Sheng, GENG Guo-hua, ZOU Lin-bo, ZHOU Ming-quan. Real spatial terrain reconstruction of first person point-of-view sketches[J]. Optics and Precision Engineering, 2020, 28(8): 1861.

第一人称视角地形轮廓草图的真实空间重建

关于本站 Cookie 的使用提示

全站搜索

第一人称视角地形轮廓草图的真实空间重建

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索