Multi-View Stereo with Asymmetric Checkerboard Propagation and Multi-Hypothesis Joint View Selection

In computer vision domain, how to fast and accurately perform multiview stereo (MVS) is still a challenging problem. In this paper we present a fast yet accurate method for 3D dense reconstruction, called AMHMVS, built on the PatchMatch based stereo algorithm. Different from the regular symmetric propagation scheme, our approach adopts an asymmetric checkerboard propagation strategy, which can adaptively make effective hypotheses expand further according to the confidence of current neighbor hypotheses. In order to aggregate visual information from multiple images better, we propose the multi-hypothesis joint view selection for each pixel, which leverages a cost matrix based on the multiple propagated hypotheses to robustly infer an appropriate aggregation subset parallel. Combined with the above two steps, our approach not only has the capacity of massively parallel computation, but also obtains high accuracy and completeness. Experiments on extensive datasets show that our method achieves more accurate and robust results, and runs faster than the competing methods.

[1]  Steven M. Seitz,et al.  The Visual Turing Test for Scene Reconstruction , 2013, 2013 International Conference on 3D Vision.

[2]  Jan-Michael Frahm,et al.  Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Tomás Pajdla,et al.  Multi-view reconstruction preserving weakly-supported surfaces , 2011, CVPR 2011.

[4]  Steven M. Seitz,et al.  Multicore bundle adjustment , 2011, CVPR 2011.

[5]  Radu Horaud,et al.  Topology-Adaptive Mesh Deformation for Surface Evolution, Morphing, and Multiview Reconstruction , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Steven M. Seitz,et al.  Photo tourism: exploring photo collections in 3D , 2006, ACM Trans. Graph..

[7]  In-So Kweon,et al.  Adaptive Support-Weight Approach for Correspondence Search , 2006, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Jan-Michael Frahm,et al.  PatchMatch Based Joint View Selection and Depthmap Estimation , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Jean Ponce,et al.  Accurate, Dense, and Robust Multiview Stereopsis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Yasuyuki Matsushita,et al.  Efficient Multiview Stereo by Random-Search and Propagation , 2014, 2014 2nd International Conference on 3D Vision.

[11]  Henrik Aanæs,et al.  Large Scale Multi-view Stereopsis Evaluation , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Torsten Sattler,et al.  A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Hendrik P. A. Lensch,et al.  Scale Robust Multi View Stereo , 2012, ECCV.

[14]  Jean-Philippe Pons,et al.  Towards high-resolution large-scale multi-view stereo , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Adam Finkelstein,et al.  PatchMatch: a randomized correspondence algorithm for structural image editing , 2009, SIGGRAPH 2009.

[16]  Pascal Fua,et al.  On benchmarking camera calibration and multi-view stereo for high resolution imagery , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Richard Szeliski,et al.  Handling occlusions in dense multi-view stereo , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[18]  Radim Sara,et al.  Refinement of Surface Mesh for Accurate Multi-View Reconstruction , 2010, Int. J. Virtual Real..

[19]  Jean-Philippe Pons,et al.  Towards high-resolution large-scale multi-view stereo , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Noah Snavely,et al.  Robust Global Translations with 1DSfM , 2014, ECCV.

[21]  Shuhan Shen,et al.  Accurate Multiple View 3D Reconstruction Using Patch-Based Stereo for Large-Scale Scenes , 2013, IEEE Transactions on Image Processing.

[22]  Carlos Hernandez,et al.  Multi-View Stereo: A Tutorial , 2015, Found. Trends Comput. Graph. Vis..

[23]  Jan-Michael Frahm,et al.  Pixelwise View Selection for Unstructured Multi-View Stereo , 2016, ECCV.

[24]  Steven M. Seitz,et al.  Occluding Contours for Multi-view Stereo , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Richard Szeliski,et al.  A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[26]  Konrad Schindler,et al.  Massively Parallel Multiview Stereopsis by Surface Normal Diffusion , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Richard Szeliski,et al.  Towards Internet-scale multi-view stereo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[28]  Carsten Rother,et al.  PatchMatch Stereo - Stereo Matching with Slanted Support Windows , 2011, BMVC.

[29]  Michael Goesele,et al.  Multi-View Stereo for Community Photo Collections , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[30]  Nanning Zheng,et al.  Stereo Matching Using Belief Propagation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  C. Zach Fast and High Quality Fusion of Depth Maps , 2008 .

[32]  Xiaoyan Hu,et al.  Least Commitment, Viewpoint-Based, Multi-view Stereo , 2012, 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission.