Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance

Recovering the 3D geometry of a purely texture-less object with generally unknown surface reflectance (e.g. non-Lambertian) is regarded as a challenging task in multi-view reconstruction. The major obstacle revolves around establishing cross-view correspondences where photometric constancy is violated. This paper proposes a simple and practical solution to overcome this challenge based on a co-located camera-light scanner device. Unlike existing solutions, we do not explicitly solve for correspondence. Instead, we argue the problem is generally well-posed by multi-view geometrical and photometric constraints, and can be solved from a small number of input views. We formulate the reconstruction task as a joint energy minimization over the surface geometry and reflectance. Despite this energy is highly non-convex, we develop an optimization algorithm that robustly recovers globally optimal shape and reflectance even from a random initialization. Extensive experiments on both simulated and real data have validated our method, and possible future extensions are discussed.

[1]  Jan-Michael Frahm,et al.  Structure-from-Motion Revisited , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Michael Breuß,et al.  Combining Shape from Shading and Stereo: A Joint Variational Method for Estimating Depth, Illumination and Albedo , 2018, International Journal of Computer Vision.

[3]  Kalyan Sunkavalli,et al.  Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image , 2018, ECCV.

[4]  Luc Van Gool,et al.  Tackling Shapes and BRDFs Head-On , 2014, 2014 2nd International Conference on 3D Vision.

[5]  Giljoo Nam,et al.  Practical SVBRDF acquisition of 3D objects with unstructured flash photography , 2018, ACM Trans. Graph..

[6]  Quan Pan,et al.  SLAM-based cooperative calibration for optical sensors array with GPS/IMU aided , 2016, 2016 International Conference on Unmanned Aircraft Systems (ICUAS).

[7]  Jannik Boll Nielsen,et al.  On optimal, minimal BRDF sampling for reflectance acquisition , 2015, ACM Trans. Graph..

[8]  Roberto Cipolla,et al.  Multiview Photometric Stereo , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Quan Pan,et al.  Robust and Efficient Relative Pose With a Multi-Camera System for Autonomous Driving in Highly Dynamic Environments , 2018, IEEE Transactions on Intelligent Transportation Systems.

[10]  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).

[11]  Jean-Denis Durou,et al.  A Splitting-Based Algorithm for Multi-view Stereopsis of Textureless Objects , 2019, SSVM.

[12]  Michael Goesele,et al.  Shading-Aware Multi-view Stereo , 2016, ECCV.

[13]  Yasuyuki Matsushita,et al.  A hand-held photometric stereo camera for 3-D modeling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[14]  Jannik Boll Nielsen,et al.  Minimal BRDF sampling for two-shot near-field reflectance acquisition , 2016, ACM Trans. Graph..

[15]  Qionghai Dai,et al.  Fusing Multiview and Photometric Stereo for 3D Reconstruction under Uncalibrated Illumination , 2011, IEEE Transactions on Visualization and Computer Graphics.

[16]  Adam Finkelstein,et al.  The Generalized PatchMatch Correspondence Algorithm , 2010, ECCV.

[17]  Marc Levoy,et al.  A volumetric method for building complex models from range images , 1996, SIGGRAPH.

[18]  Michael A. Saunders,et al.  LSQR: An Algorithm for Sparse Linear Equations and Sparse Least Squares , 1982, TOMS.

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

[20]  Michael Goesele,et al.  Consensus Multi-View Photometric Stereo , 2012, DAGM/OAGM Symposium.

[21]  Robert Hooke,et al.  `` Direct Search'' Solution of Numerical and Statistical Problems , 1961, JACM.

[22]  Zhe Wu,et al.  Multi-view Photometric Stereo with Spatially Varying Isotropic Materials , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Ko Nishino,et al.  Multiview Shape and Reflectance from Natural Illumination , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Roberto Cipolla,et al.  A Differential Volumetric Approach to Multi-View Photometric Stereo , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Xi Wang,et al.  Non-Lambertian Photometric Stereo Network Based on Inverse Reflectance Model With Collocated Light , 2020, IEEE Transactions on Image Processing.

[26]  Daniel Cremers,et al.  Large displacement optical flow computation withoutwarping , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[27]  J. Nocedal Updating Quasi-Newton Matrices With Limited Storage , 1980 .

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

[29]  Boxin Shi,et al.  Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials , 2020, IEEE Transactions on Image Processing.

[30]  Jian Wang,et al.  Reflectance Capture Using Univariate Sampling of BRDFs , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[31]  Szymon Rusinkiewicz,et al.  A New Change of Variables for Efficient BRDF Representation , 1998, Rendering Techniques.

[32]  A. Laurentini,et al.  The Visual Hull Concept for Silhouette-Based Image Understanding , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Masatoshi Okutomi,et al.  Multi-view Inverse Rendering Under Arbitrary Illumination and Albedo , 2016, ECCV.

[34]  Hongdong Li,et al.  Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[35]  Li Zhang,et al.  Shape and motion under varying illumination: unifying structure from motion, photometric stereo, and multiview stereo , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[36]  David J. Kriegman,et al.  Passive photometric stereo from motion , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[37]  Zhe Wu,et al.  A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo , 2019, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  S. Ullman The interpretation of structure from motion , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[39]  Wojciech Matusik,et al.  A data-driven reflectance model , 2003, ACM Trans. Graph..

[40]  Yasuyuki Matsushita,et al.  Robust Multiview Photometric Stereo Using Planar Mesh Parameterization , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Gernot Riegler,et al.  On Joint Estimation of Pose, Geometry and svBRDF From a Handheld Scanner , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).