pith. sign in

arxiv: 1907.02890 · v1 · pith:X6THBBX5new · submitted 2019-07-05 · 💻 cs.CV

A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching

Jiaqi Yang , Ke Xian , Peng Wang , Yanning Zhang This is my paper

Pith reviewed 2026-05-25 02:15 UTC · model grok-4.3

classification 💻 cs.CV
keywords correspondence grouping3D rigid matchingperformance evaluationpoint cloudsinlier retrievalbenchmarksperturbationscomputer vision
0
0 comments X

The pith

Nine correspondence grouping methods for 3D rigid data are evaluated on benchmarks with varied perturbations to identify their merits and shortcomings.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper conducts experiments on nine state-of-the-art methods for grouping consistent correspondences from initial 3D feature matches. The tests use three benchmarks covering shape retrieval, object recognition, and point cloud registration, plus perturbations including noise, density changes, clutter, occlusion, and partial overlap. Results allow a summary of each method's traits under different conditions, showing how performance varies with inlier ratios and spatial distributions. This matters because better grouping leads to higher precision and recall, supporting more accurate 3D transformation estimation in computer vision tasks.

Core claim

The paper establishes that deploying experiments across diverse application scenarios and nuisances results in different spatial distributions and inlier ratios of initial feature correspondences, enabling a thorough evaluation. Based on the outcomes, it provides a summary of the traits, merits, and demerits of the evaluated approaches and indicates some potential future research directions.

What carries the argument

The evaluation protocol using multiple benchmarks and perturbation types to assess how well each method retrieves inliers from initial matches, thereby improving precision, recall, and transformation estimation accuracy.

If this is right

  • Methods perform differently depending on the specific application context and type of perturbation present.
  • Some approaches maintain higher precision and recall when initial correspondences have low inlier ratios.
  • The evaluation highlights which methods are more robust to noise or occlusion in point cloud data.
  • Future research can build on identified shortcomings to develop improved grouping algorithms.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • New methods could be designed to combine the strengths observed in different evaluated approaches for better overall performance.
  • The findings suggest prioritizing robustness to partial overlap in future correspondence grouping research.
  • Extending the benchmarks to include more real-world sensor data could further validate the conclusions.

Load-bearing premise

The chosen benchmarks, perturbation types, and initial correspondence generators are representative enough of real-world 3D rigid matching scenarios to allow general conclusions about method performance.

What would settle it

If performance rankings of the methods change substantially when evaluated on additional real-world datasets with untested combinations of perturbations, this would indicate the evaluation's conclusions do not generalize.

Figures

Figures reproduced from arXiv: 1907.02890 by Jiaqi Yang, Ke Xian, Peng Wang, Yanning Zhang.

Figure 1
Figure 1. Figure 1: Illustration of local feature-based matching paradigm, where the [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: Spatial distributions of corresponding keypoints (detector: [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 2
Figure 2. Figure 2: Sample views (visualized in mesh representation) from (a) [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: Information in terms of inlier ratio and the number of inliers for the initial correspondences when confronted with different challenges. Details [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Comparison of (left) a clean rigid data and its (middle) noisy and [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Precision, recall, and F-score performance of selected methods in Sect. [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Rigid registration performance of selected methods in Sect. [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Precision results of GC and RANSAC on each matching pair from [PITH_FULL_IMAGE:figures/full_fig_p011_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Computational efficiency with regards to different sizes of the [PITH_FULL_IMAGE:figures/full_fig_p012_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Visual results of the grouped inlier sets by evaluated methods on sample data from the experimental datasets. [PITH_FULL_IMAGE:figures/full_fig_p013_10.png] view at source ↗
read the original abstract

Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision. While a number of correspondence selection methods have been proposed in recent years, their advantages and shortcomings remain unclear regarding different applications and perturbations. To fill this gap, this paper gives a comprehensive evaluation of nine state-of-the-art 3D correspondence grouping methods. A good correspondence grouping algorithm is expected to retrieve as many as inliers from initial feature matches, giving a rise in both precision and recall as well as facilitating accurate transformation estimation. Toward this rule, we deploy experiments on three benchmarks with different application contexts including shape retrieval, 3D object recognition, and point cloud registration together with various perturbations such as noise, point density variation, clutter, occlusion, partial overlap, different scales of initial correspondences, and different combinations of keypoint detectors and descriptors. The rich variety of application scenarios and nuisances result in different spatial distributions and inlier ratios of initial feature correspondences, thus enabling a thorough evaluation. Based on the outcomes, we give a summary of the traits, merits, and demerits of evaluated approaches and indicate some potential future research directions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper conducts an empirical performance evaluation of nine state-of-the-art 3D correspondence grouping methods for rigid data matching. Experiments are run on three benchmarks (shape retrieval, 3D object recognition, point cloud registration) under perturbations including noise, density variation, clutter, occlusion, partial overlap, varying correspondence scales, and different keypoint detector/descriptor pairs. The central contribution is a summary of each method's traits, merits, and demerits together with suggested future research directions.

Significance. A broad, controlled comparison across application contexts and nuisance types can help practitioners select grouping methods and can highlight open problems for the community. The work's strength lies in its purely empirical design with no fitted parameters or circular derivations.

major comments (1)
  1. [Abstract] Abstract: the claim that the 'rich variety of application scenarios and nuisances result in different spatial distributions and inlier ratios of initial feature correspondences, thus enabling a thorough evaluation' is load-bearing for the general merit/demerit summaries, yet the manuscript provides no external validation (e.g., against sensor-specific artifacts, newer datasets, or real-world capture statistics) that the chosen benchmarks and perturbation models are representative.
minor comments (2)
  1. The paper would be strengthened by releasing code or at minimum listing all implementation parameters and random seeds used for the reported metrics.
  2. Figure captions and axis labels in the result plots could be made more self-contained to improve readability without reference to the main text.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback. We address the single major comment below, focusing on the representativeness of the evaluation.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that the 'rich variety of application scenarios and nuisances result in different spatial distributions and inlier ratios of initial feature correspondences, thus enabling a thorough evaluation' is load-bearing for the general merit/demerit summaries, yet the manuscript provides no external validation (e.g., against sensor-specific artifacts, newer datasets, or real-world capture statistics) that the chosen benchmarks and perturbation models are representative.

    Authors: We acknowledge the referee's point that the abstract claim is central to the merit/demerit summaries. The three benchmarks (shape retrieval, 3D object recognition, and point cloud registration) and the listed perturbations (noise, density variation, clutter, occlusion, partial overlap, correspondence scale, and detector/descriptor pairs) were selected because they are established in the 3D vision literature and produce the varied inlier distributions described. However, the manuscript does not include new external validation against sensor-specific artifacts, newer datasets, or real-world capture statistics. We can revise the abstract to qualify the claim as 'enabling a thorough evaluation across these standard benchmarks and perturbations' and add a short limitations paragraph in the discussion section referencing the reliance on prior benchmark validation. This is a partial revision that clarifies scope without new experiments. revision: partial

Circularity Check

0 steps flagged

No circularity: purely empirical benchmark evaluation with no derivations or fitted predictions

full rationale

The paper conducts an empirical performance comparison of nine correspondence grouping methods across three benchmarks and multiple perturbations. Its central output is a summary of traits/merits/demerits drawn directly from experimental results (precision, recall, transformation accuracy). No equations, first-principles derivations, parameter fittings, or predictions are present that could reduce to inputs by construction. Self-citations, if any, are not load-bearing for any claimed result. The evaluation is self-contained against the stated external benchmarks and perturbations.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Empirical evaluation paper; contains no free parameters, mathematical axioms, or invented entities.

pith-pipeline@v0.9.0 · 5748 in / 927 out tokens · 32084 ms · 2026-05-25T02:15:16.292491+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

58 extracted references · 1 canonical work pages · 1 internal anchor

  1. [1]

    Aligning point cloud views using persistent feature histograms,

    R. B. Rusu, N. Blodow, Z. C. Marton, and M. Beetz, “Aligning point cloud views using persistent feature histograms,” in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems , 2008, pp. 3384–3391

    2008

  2. [2]

    A fast and robust local descriptor for 3d point cloud registration,

    J. Yang, Z. Cao, and Q. Zhang, “A fast and robust local descriptor for 3d point cloud registration,” Information Sciences, vol. 346, pp. 163–179, 2016

    2016

  3. [3]

    Shot: Unique signatures of histograms for surface and texture description,

    S. Salti, F. Tombari, and L. Di Stefano, “Shot: Unique signatures of histograms for surface and texture description,” Computer Vision and Image Understanding, vol. 125, pp. 251–264, 2014

    2014

  4. [4]

    Rotational projection statistics for 3d local surface description and object recognition,

    Y. Guo, F. Sohel, M. Bennamoun, M. Lu, and J. Wan, “Rotational projection statistics for 3d local surface description and object recognition,” International Journal of Computer Vision, vol. 105, no. 1, pp. 63–86, 2013

    2013

  5. [5]

    Shrec 2011: Robust feature detection and description benchmark,

    E. Boyer, A. Bronstein, M. Bronstein, B. Bustos, T. Darom, R. Ho- raud, I. Hotz, Y. Kelle, J. Keustermans, A. Kovnatsky et al., “Shrec 2011: Robust feature detection and description benchmark,” in Proc. Eurographics Workshop on 3D Object Retrieval, 2011

    2011

  6. [6]

    When 2.5 d is not enough: Simultaneous reconstruction, segmentation and recognition on dense slam,

    K. Tateno, F. Tombari, and N. Navab, “When 2.5 d is not enough: Simultaneous reconstruction, segmentation and recognition on dense slam,” in Proc. IEEE International Conference on Robotics and Automation. IEEE, 2016, pp. 2295–2302

    2016

  7. [7]

    Automatic cor- respondence for 3d modeling: an extensive review,

    A. S. Mian, M. Bennamoun, and R. A. Owens, “Automatic cor- respondence for 3d modeling: an extensive review,” International Journal of Shape Modeling, vol. 11, no. 02, pp. 253–291, 2005

    2005

  8. [8]

    3d object recognition in cluttered scenes with local surface features: A sur- vey,

    Y. Guo, M. Bennamoun, F. Sohel, M. Lu, and J. Wan, “3d object recognition in cluttered scenes with local surface features: A sur- vey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 11, pp. 2270–2287, 2014

    2014

  9. [9]

    Performance evaluation of 3d keypoint detectors,

    F. Tombari, S. Salti, and L. Di Stefano, “Performance evaluation of 3d keypoint detectors,” International Journal of Computer Vision , vol. 102, no. 1-3, pp. 198–220, 2013

    2013

  10. [10]

    A comprehensive performance evaluation of 3d local feature descriptors,

    Y. Guo, M. Bennamoun, F. Sohel, M. Lu, J. Wan, and N. M. Kwok, “A comprehensive performance evaluation of 3d local feature descriptors,” International Journal of Computer Vision, vol. 116, no. 1, pp. 66–89, 2016

    2016

  11. [11]

    The effect of spatial information characterization on 3d local feature descriptors: A quantitative evaluation,

    J. Yang, Q. Zhang, and Z. Cao, “The effect of spatial information characterization on 3d local feature descriptors: A quantitative evaluation,” Pattern Recognition, vol. 66, pp. 375–391, 2017

    2017

  12. [12]

    Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,

    M. A. Fischler and R. C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM , vol. 24, no. 6, pp. 381–395, 1981

    1981

  13. [13]

    Usac: a universal framework for random sample consensus

    R. Raguram, O. Chum, M. Pollefeys, J. Matas, and J.-M. Frahm, “Usac: a universal framework for random sample consensus.” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 35, no. 8, pp. 2022–2038, 2013

    2022

  14. [14]

    Gms: Grid-based motion statistics for fast, ultra-robust feature correspondence,

    J. Bian, W.-Y. Lin, Y. Matsushita, S.-K. Yeung, T.-D. Nguyen, and M.-M. Cheng, “Gms: Grid-based motion statistics for fast, ultra-robust feature correspondence,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition . IEEE, 2017, pp. 2828– 2837

    2017

  15. [15]

    Locality preserving matching,

    J. Ma, J. Zhao, J. Jiang, H. Zhou, and X. Guo, “Locality preserving matching,” International Journal of Computer Vision, pp. 1–20, 2018

    2018

  16. [16]

    A spectral technique for correspon- dence problems using pairwise constraints,

    M. Leordeanu and M. Hebert, “A spectral technique for correspon- dence problems using pairwise constraints,” in Proc. International Conference on Computer Vision, vol. 2. IEEE, 2005, pp. 1482–1489

    2005

  17. [17]

    3d free-form object recognition in range images using local surface patches,

    H. Chen and B. Bhanu, “3d free-form object recognition in range images using local surface patches,” Pattern Recognition Letters , vol. 28, no. 10, pp. 1252–1262, 2007

    2007

  18. [18]

    On the repeatability and quality of keypoints for local feature-based 3d object retrieval from cluttered scenes,

    A. Mian, M. Bennamoun, and R. Owens, “On the repeatability and quality of keypoints for local feature-based 3d object retrieval from cluttered scenes,” International Journal of Computer Vision , vol. 89, no. 2-3, pp. 348–361, 2010

    2010

  19. [19]

    Object recognition in 3d scenes with occlusions and clutter by hough voting,

    F. Tombari and L. Di Stefano, “Object recognition in 3d scenes with occlusions and clutter by hough voting,” in Proc. Pacific-Rim Symposium on Image and Video Technology. IEEE, 2010, pp. 349–355

    2010

  20. [20]

    A scale in- dependent selection process for 3d object recognition in cluttered scenes,

    E. Rodol `a, A. Albarelli, F. Bergamasco, and A. Torsello, “A scale in- dependent selection process for 3d object recognition in cluttered scenes,” International Journal of Computer Vision , vol. 102, no. 1-3, pp. 129–145, 2013

    2013

  21. [21]

    In search of inliers: 3d correspondence by local and global voting,

    A. G. Buch, Y. Yang, N. Kr ¨uger, and H. G. Petersen, “In search of inliers: 3d correspondence by local and global voting,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2014, pp. 2075–2082

    2014

  22. [22]

    Ranking 3d feature cor- respondences via consistency voting,

    J. Yang, Y. Xiao, Z. Cao, and W. Yang, “Ranking 3d feature cor- respondences via consistency voting,” Pattern Recognition Letters , vol. 117, pp. 1–8, 2019

    2019

  23. [23]

    Guaranteed outlier removal for point cloud registration with correspondences,

    ´A. P . Bustos and T.-J. Chin, “Guaranteed outlier removal for point cloud registration with correspondences,” IEEE Transactions on JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 15 Pattern Analysis and Machine Intelligence , vol. 40, no. 12, pp. 2868– 2882, 2018

    2015

  24. [24]

    Distinctive image features from scale-invariant key- points,

    D. G. Lowe, “Distinctive image features from scale-invariant key- points,” International Journal of Computer Vision , vol. 60, no. 2, pp. 91–110, 2004

    2004

  25. [25]

    Performance evaluation of 3d correspondence grouping algorithms,

    J. Yang, K. Xian, Y. Xiao, and Z. Cao, “Performance evaluation of 3d correspondence grouping algorithms,” in Proc. International Conference on 3D Vision. IEEE, 2017, pp. 467–476

    2017

  26. [26]

    Comparing 3d descriptors for local search of craniofacial landmarks,

    F. M. Sukno, J. L. Waddington, and P . F. Whelan, “Comparing 3d descriptors for local search of craniofacial landmarks,” in Proc. International Symposium on Visual Computing . Springer, 2012, pp. 92–103

    2012

  27. [27]

    Evaluation of 3d feature descriptors for multi-modal data registration,

    H. Kim and A. Hilton, “Evaluation of 3d feature descriptors for multi-modal data registration,” in Proc. International Conference on 3D Vision. IEEE, 2013, pp. 119–126

    2013

  28. [28]

    Local shape feature fusion for improved matching, pose estimation and 3d object recognition,

    A. G. Buch, H. G. Petersen, and N. Kr ¨uger, “Local shape feature fusion for improved matching, pose estimation and 3d object recognition,” SpringerPlus, vol. 5, no. 1, p. 297, 2016

    2016

  29. [29]

    On the repeatability of the local reference frame for partial shape matching,

    A. Petrelli and L. D. Stefano, “On the repeatability of the local reference frame for partial shape matching,” in Proc. IEEE Interna- tional Conference on Computer Vision, 2011, pp. 2244–2251

    2011

  30. [30]

    Toward the repeatability and robustness of the local reference frame for 3d shape matching: An evaluation,

    J. Yang, Y. Xiao, and Z. Cao, “Toward the repeatability and robustness of the local reference frame for 3d shape matching: An evaluation,” IEEE Transactions on Image Processing , vol. 27, no. 8, pp. 3766–3781, 2018

    2018

  31. [31]

    Shrec 2010: robust feature detection and description benchmark,

    A. M. Bronstein, M. M. Bronstein, B. Bustos, U. Castellani, M. Crisani, B. Falcidieno, L. J. Guibas, I. Kokkinos, V . Murino, M. Ovsjanikov et al. , “Shrec 2010: robust feature detection and description benchmark,” Eurographics Workshop on 3D Object Re- trieval, vol. 2, no. 5, p. 6, 2010

    2010

  32. [32]

    On the affin- ity between 3d detectors and descriptors,

    S. Salti, A. Petrelli, F. Tombari, and L. Di Stefano, “On the affin- ity between 3d detectors and descriptors,” in Proc. International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission. IEEE, 2012, pp. 424–431

    2012

  33. [33]

    Comparison of 3d interest point detectors and descriptors for point cloud fusion,

    R. H ¨ansch, T. Weber, and O. Hellwich, “Comparison of 3d interest point detectors and descriptors for point cloud fusion,” ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 2, no. 3, p. 57, 2014

    2014

  34. [34]

    Persistent point feature histograms for 3d point clouds,

    R. B. Rusu, Z. C. Marton, N. Blodow, and M. Beetz, “Persistent point feature histograms for 3d point clouds,” in Proc. International Conference on Intelligent Autonomous Systems, 2008, pp. 119–128

    2008

  35. [35]

    Rotational contour signatures for both real-valued and binary feature representations of 3d local shape,

    J. Yang, Q. Zhang, K. Xian, Y. Xiao, and Z. Cao, “Rotational contour signatures for both real-valued and binary feature representations of 3d local shape,” Computer Vision and Image Understanding , vol. 160, pp. 133–147, 2017

    2017

  36. [36]

    Local point pair feature histogram for accurate 3d matching,

    A. G. Buch, D. Kraft, S. Robotics, and D. Odense, “Local point pair feature histogram for accurate 3d matching,” in Proc. British Machine Vision Conference, 2018

    2018

  37. [37]

    A comparative analysis of ransac techniques leading to adaptive real-time ran- dom sample consensus,

    R. Raguram, J.-M. Frahm, and M. Pollefeys, “A comparative analysis of ransac techniques leading to adaptive real-time ran- dom sample consensus,” in Proc. European Conference on Computer Vision. Springer, 2008, pp. 500–513

    2008

  38. [38]

    MatchBench: An Evaluation of Feature Matchers

    J. Bian, R. Yang, Y. Liu, L. Zhang, M.-M. Cheng, I. Reid, and W. Wu, “Matchbench: An evaluation of feature matchers,” arXiv preprint arXiv:1808.02267, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  39. [39]

    Three-dimensional model-based object recognition and segmentation in cluttered scenes,

    A. S. Mian, M. Bennamoun, and R. Owens, “Three-dimensional model-based object recognition and segmentation in cluttered scenes,” IEEE Transactions on Pattern Analysis and Machine Intel- ligence, vol. 28, no. 10, pp. 1584–1601, 2006

    2006

  40. [40]

    Unique signatures of his- tograms for local surface description,

    F. Tombari, S. Salti, and L. Di Stefano, “Unique signatures of his- tograms for local surface description,” in Proc. European Conference on Computer Vision, 2010, pp. 356–369

    2010

  41. [41]

    A threshold selection method from gray-level his- tograms,

    N. Otsu, “A threshold selection method from gray-level his- tograms,” Automatica, vol. 11, no. 285-296, pp. 23–27, 1975

    1975

  42. [42]

    Automatic panoramic image stitching using invariant features,

    M. Brown and D. G. Lowe, “Automatic panoramic image stitching using invariant features,” International Journal of Computer Vision , vol. 74, no. 1, pp. 59–73, 2007

    2007

  43. [43]

    Mlesac: A new robust estimator with application to estimating image geometry,

    P . H. Torr and A. Zisserman, “Mlesac: A new robust estimator with application to estimating image geometry,” Computer Vision and Image Understanding, vol. 78, no. 1, pp. 138–156, 2000

    2000

  44. [44]

    Matching with prosac-progressive sample consensus,

    O. Chum and J. Matas, “Matching with prosac-progressive sample consensus,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, vol. 1. IEEE, 2005, pp. 220–226

    2005

  45. [45]

    Normalized cuts and image segmentation,

    J. Shi and J. Malik, “Normalized cuts and image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 22, no. 8, pp. 888–905, 2000

    2000

  46. [46]

    Segmen- tation of multiple salient closed contours from real images,

    S. Mahamud, L. R. Williams, K. K. Thornber, and K. Xu, “Segmen- tation of multiple salient closed contours from real images,” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 25, no. 4, pp. 433–444, 2003

    2003

  47. [47]

    Surface matching for object recog- nition in complex three-dimensional scenes,

    A. E. Johnson and M. Hebert, “Surface matching for object recog- nition in complex three-dimensional scenes,” Image and Vision Computing, vol. 16, no. 9, pp. 635–651, 1998

    1998

  48. [48]

    Method and means for recognizing complex patterns,

    H. P . VC, “Method and means for recognizing complex patterns,” 1962, uS Patent 3,069,654

    1962

  49. [49]

    J. W. Weibull, Evolutionary game theory. MIT press, 1997

    1997

  50. [50]

    A novel repre- sentation and feature matching algorithm for automatic pairwise registration of range images,

    A. S. Mian, M. Bennamoun, and R. A. Owens, “A novel repre- sentation and feature matching algorithm for automatic pairwise registration of range images,” International Journal of Computer Vision, vol. 66, no. 1, pp. 19–40, 2006

    2006

  51. [51]

    A volumetric method for building complex models from range images,

    B. Curless and M. Levoy, “A volumetric method for building complex models from range images,” in Proc. Annual Conference on Computer Graphics and Interactive Techniques, 1996, pp. 303–312

    1996

  52. [52]

    Method for registration of 3-d shapes,

    P . J. Besl and N. D. McKay, “Method for registration of 3-d shapes,” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 14, no. 2, pp. 239–256, 1992

    1992

  53. [53]

    Harris 3d: a robust extension of the harris operator for interest point detection on 3d meshes,

    I. Sipiran and B. Bustos, “Harris 3d: a robust extension of the harris operator for interest point detection on 3d meshes,” The Visual Computer, vol. 27, no. 11, pp. 963–976, 2011

    2011

  54. [54]

    Using spin images for efficient object recognition in cluttered 3d scenes,

    A. E. Johnson and M. Hebert, “Using spin images for efficient object recognition in cluttered 3d scenes,” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 21, no. 5, pp. 433– 449, 1999

    1999

  55. [55]

    Recent advances in mesh morphing,

    M. Alexa, “Recent advances in mesh morphing,” in Proc. Computer Graphics Forum , vol. 21, no. 2. Wiley Online Library, 2002, pp. 173–198

    2002

  56. [56]

    Intrinsic shape signatures: A shape descriptor for 3d object recognition,

    Y. Zhong, “Intrinsic shape signatures: A shape descriptor for 3d object recognition,” in Proc. International Conference on Computer Vision Workshops. IEEE, 2009, pp. 689–696

    2009

  57. [57]

    3d is here: Point cloud library (pcl),

    R. B. Rusu and S. Cousins, “3d is here: Point cloud library (pcl),” in Proc. IEEE International Conference on Robotics and Automation , 2011, pp. 1–4

    2011

  58. [58]

    Elastic net constraints for shape matching,

    E. Rodol `a, A. Torsello, T. Harada, Y. Kuniyoshi, and D. Cremers, “Elastic net constraints for shape matching,” in Proc. IEEE Interna- tional Conference on Computer Vision, 2013, pp. 1169–1176

    2013