Advertisement

RANSAC-Flow: Generic Two-Stage Image Alignment

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12349)

Abstract

This paper considers the generic problem of dense alignment between two images, whether they be two frames of a video, two widely different views of a scene, two paintings depicting similar content, etc. Whereas each such task is typically addressed with a domain-specific solution, we show that a simple unsupervised approach performs surprisingly well across a range of tasks. Our main insight is that parametric and non-parametric alignment methods have complementary strengths. We propose a two-stage process: first, a feature-based parametric coarse alignment using one or more homographies, followed by non-parametric fine pixel-wise alignment. Coarse alignment is performed using RANSAC on off-the-shelf deep features. Fine alignment is learned in an unsupervised way by a deep network which optimizes a standard structural similarity metric (SSIM) between the two images, plus cycle-consistency. Despite its simplicity, our method shows competitive results on a range of tasks and datasets, including unsupervised optical flow on KITTI, dense correspondences on Hpatches, two-view geometry estimation on YFCC100M, localization on Aachen Day-Night, and, for the first time, fine alignment of artworks on the Brughel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/RANSAC-Flow/.

Keywords

Unsupervised dense image alignment Applications to art 

Notes

Acknowledgements

This work was supported by ANR project EnHerit ANR-17-CE23-0008, project Rapid Tabasco, NSF IIS-1633310, grants from SAP and Berkeley CLTC, and gifts from Adobe. We thank Shiry Ginosar, Thibault Groueix and Michal Irani for helpful discussions, and Elizabeth Alice Honig for her help in building the Brueghel dataset.

Supplementary material

504439_1_En_36_MOESM1_ESM.pdf (126 kb)
Supplementary material 1 (pdf 125 KB)
504439_1_En_36_MOESM2_ESM.pdf (3.7 mb)
Supplementary material 2 (pdf 3817 KB)
504439_1_En_36_MOESM3_ESM.pdf (1.2 mb)
Supplementary material 3 (pdf 1206 KB)

References

  1. 1.
    Brueghel family: Jan brueghel the elder. The brueghel family database. University of California, Berkeley. http://www.janbrueghel.net/. Accessed 16 Oct 2018
  2. 2.
    Ahmadi, A., Patras, I.: Unsupervised convolutional neural networks for motion estimation. In: International Conference on Image Processing (2016)Google Scholar
  3. 3.
    Aubry, M., Russell, B.C., Sivic, J.: Painting-to-3D model alignment via discriminative visual elements. ACM Trans. Graph. (ToG) 33, 1–14 (2014)Google Scholar
  4. 4.
    Bailer, C., Taetz, B., Stricker, D.: Flow fields: dense correspondence fields for highly accurate large displacement optical flow estimation. In: Proceedings of the IEEE International Conference on Computer Vision (2015)Google Scholar
  5. 5.
    Balntas, V., Lenc, K., Vedaldi, A., Mikolajczyk, K.: Hpatches: a benchmark and evaluation of handcrafted and learned local descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  6. 6.
    Barath, D., Matas, J.: Graph-cut ransac. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  7. 7.
    Barath, D., Matas, J.: Progressive-x: efficient, anytime, multi-model fitting algorithm. In: Proceedings of the IEEE International Conference on Computer Vision (2019)Google Scholar
  8. 8.
    Barath, D., Matas, J., Noskova, J.: Magsac: marginalizing sample consensus. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  9. 9.
    Brox, T., Bregler, C., Malik, J.: Large displacement optical flow. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  10. 10.
    Cao, Z., Kar, A., Hane, C., Malik, J.: Learning independent object motion from unlabelled stereoscopic videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  11. 11.
    Cech, J., Matas, J., Perdoch, M.: Efficient sequential correspondence selection by cosegmentation. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1568–1581 (2010)CrossRefGoogle Scholar
  12. 12.
    Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: Advances in Neural Information Processing Systems (2016)Google Scholar
  13. 13.
    Debevec, P.E., Taylor, C.J., Malik, J.: Modeling and rendering architecture from photographs: A hybrid geometry-and image-based approach. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques (1996)Google Scholar
  14. 14.
    DeTone, D., Malisiewicz, T., Rabinovich, A.: Superpoint: self-supervised interest point detection and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2018)Google Scholar
  15. 15.
    Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision (2015)Google Scholar
  16. 16.
    Dusmanu, M., et al.: D2-net: a trainable CNN for joint description and detection of local features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  17. 17.
    Fernando, B., Tommasi, T., Tuytelaars, T.: Location recognition over large time lags. Comput. Vis. Image Underst. 139, 21–28 (2015)CrossRefGoogle Scholar
  18. 18.
    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)zbMATHGoogle Scholar
  20. 20.
    He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)Google Scholar
  21. 21.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  22. 22.
    Hu, Y., Song, R., Li, Y.: Efficient coarse-to-fine patchmatch for large displacement optical flow. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  23. 23.
    Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  24. 24.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)Google Scholar
  25. 25.
    Irani, M., Anandan, P., Cohen, M.: Direct recovery of planar-parallax from multiple frames. IEEE Trans. Pattern Anal. Mach. Intell. 24, 1528–1534 (2002)CrossRefGoogle Scholar
  26. 26.
    Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (2015)Google Scholar
  27. 27.
    Jason, J.Y., Harley, A.W., Derpanis, K.G.: Back to basics: unsupervised learning of optical flow via brightness constancy and motion smoothness. In: Proceedings of the European Conference on Computer Vision (2016)Google Scholar
  28. 28.
    Kim, S., Lin, S., Jeon, S.R., Min, D., Sohn, K.: Recurrent transformer networks for semantic correspondence. In: Advances in Neural Information Processing Systems (2018)Google Scholar
  29. 29.
    Kim, S., Min, D., Ham, B., Jeon, S., Lin, S., Sohn, K.: Fcss: fully convolutional self-similarity for dense semantic correspondence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  30. 30.
    Kim, S., Min, D., Jeong, S., Kim, S., Jeon, S., Sohn, K.: Semantic attribute matching networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  31. 31.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference for Learning Representations (2014)Google Scholar
  32. 32.
    Kong, S., Fowlkes, C.: Multigrid predictive filter flow for unsupervised learning on videos. arXiv preprint arXiv:1904.01693 (2019)
  33. 33.
    Kumar, R., Anandan, P., Hanna, K.: Direct recovery of shape from multiple views: a parallax based approach. In: Proceedings of 12th International Conference on Pattern Recognition (1994)Google Scholar
  34. 34.
    Lai, Z., Xie, W.: Self-supervised learning for video correspondence flow. In: BMVC (2019)Google Scholar
  35. 35.
    Larsson, M., Stenborg, E., Hammarstrand, L., Pollefeys, M., Sattler, T., Kahl, F.: A cross-season correspondence dataset for robust semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  36. 36.
    Laskar, Z., Melekhov, I., Tavakoli, H.R., Ylioinas, J., Kannala, J.: Geometric image correspondence verification by dense pixel matching. In: Winter Conference on Applications of Computer Vision (2020)Google Scholar
  37. 37.
    Li, Z., Snavely, N.: Megadepth: learning single-view depth prediction from internet photos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  38. 38.
    Liu, C., Yuen, J., Torralba, A.: Sift flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33, 978–994 (2010)CrossRefGoogle Scholar
  39. 39.
    Long, J.L., Zhang, N., Darrell, T.: Do convnets learn correspondence? In: Advances in Neural Information Processing Systems (2014)Google Scholar
  40. 40.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004)CrossRefGoogle Scholar
  41. 41.
    Lucas, B.D., Kanade, T., et al.: An iterative image registration technique with an application to stereo vision (1981)Google Scholar
  42. 42.
    Luo, Z., et al.: Contextdesc: local descriptor augmentation with cross-modality context. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  43. 43.
    Luo, Z., et al.: Geodesc: learning local descriptors by integrating geometry constraints. In: Proceedings of the European Conference on Computer Vision (2018)Google Scholar
  44. 44.
    Maddern, W., Pascoe, G., Linegar, C., Newman, P.: 1 year, 1000 km: the oxford robotcar dataset. Int. J. Rob. Res. 36, 3–15 (2017)CrossRefGoogle Scholar
  45. 45.
    Magri, L., Fusiello, A.: T-linkage: a continuous relaxation of j-linkage for multi-model fitting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)Google Scholar
  46. 46.
    Magri, L., Fusiello, A.: Multiple structure recovery via robust preference analysis. Image Vis. Comp. 67, 1–15 (2017)CrossRefGoogle Scholar
  47. 47.
    Melekhov, I., Tiulpin, A., Sattler, T., Pollefeys, M., Rahtu, E., Kannala, J.: Dgc-net: dense geometric correspondence network. In: Winter Conference on Applications of Computer Vision (2019)Google Scholar
  48. 48.
    Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  49. 49.
    Mishchuk, A., Mishkin, D., Radenovic, F., Matas, J.: Working hard to know your neighbor’s margins: local descriptor learning loss. In: Advances in Neural Information Processing Systems (2017)Google Scholar
  50. 50.
    Mishkin, D., Matas, J., Perdoch, M.: Mods: fast and robust method for two-view matching. Comput. Vis. Image Underst. 141, 81–93 (2015)CrossRefGoogle Scholar
  51. 51.
    Mishkin, D., Radenovic, F., Matas, J.: Repeatability is not enough: learning affine regions via discriminability. In: Proceedings of the European Conference on Computer Vision (2018)Google Scholar
  52. 52.
    Moo Yi, K., Trulls, E., Ono, Y., Lepetit, V., Salzmann, M., Fua, P.: Learning to find good correspondences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  53. 53.
    Noh, H., Araujo, A., Sim, J., Weyand, T., Han, B.: Large-scale image retrieval with attentive deep local features. In: Proceedings of the IEEE International Conference on Computer Vision (2017)Google Scholar
  54. 54.
    Plötz, T., Roth, S.: Neural nearest neighbors networks. In: Advances in Neural Information Processing Systems (2018)Google Scholar
  55. 55.
    Prune, T., Martin, D., Radu, T.: GLU-Net: global-local universal network for dense flow and correspondences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)Google Scholar
  56. 56.
    Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  57. 57.
    Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (2017)Google Scholar
  58. 58.
    Raguram, R., Chum, O., Pollefeys, M., Matas, J., Frahm, J.M.: Usac: a universal framework for random sample consensus. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2022–2038 (2012)CrossRefGoogle Scholar
  59. 59.
    Ranftl, R., Koltun, V.: Deep fundamental matrix estimation. In: Proceedings of the European Conference on Computer Vision (2018)Google Scholar
  60. 60.
    Ren, Z., Yan, J., Ni, B., Liu, B., Yang, X., Zha, H.: Unsupervised deep learning for optical flow estimation. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar
  61. 61.
    Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Epicflow: edge-preserving interpolation of correspondences for optical flow. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  62. 62.
    Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Deepmatching: hierarchical deformable dense matching. Int. J. Comput. Vis. 120, 300–323 (2016) MathSciNetCrossRefGoogle Scholar
  63. 63.
    Revaud, J., Weinzaepfel, P., de Souza, C.R., Humenberger, M.: R2D2: repeatable and reliable detector and descriptor. In: Advances in Neural Information Processing Systems (2019)Google Scholar
  64. 64.
    Riba, E., Mishkin, D., Ponsa, D., Rublee, E., Bradski, G.: Kornia: an open source differentiable computer vision library for pytorch. In: Winter Conference on Applications of Computer Vision (2020)Google Scholar
  65. 65.
    Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  66. 66.
    Rocco, I., Cimpoi, M., Arandjelović, R., Torii, A., Pajdla, T., Sivic, J.: Neighbourhood consensus networks. In: Advances in Neural Information Processing Systems (2018)Google Scholar
  67. 67.
    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention (2015)Google Scholar
  68. 68.
    Sattler, T., et al.: Benchmarking 6dof outdoor visual localization in changing conditions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  69. 69.
    Sattler, T., Weyand, T., Leibe, B., Kobbelt, L.: Image retrieval for image-based localization revisited. In: BMVC (2012)Google Scholar
  70. 70.
    Sawhney, H.S.: 3D geometry from planar parallax. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (1994)Google Scholar
  71. 71.
    Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  72. 72.
    Shen, X., Efros, A.A., Aubry, M.: Discovering visual patterns in art collections with spatially-consistent feature learning. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  73. 73.
    Shocher, A., Cohen, N., Irani, M.: "zero-shot" super-resolution using deep internal learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  74. 74.
    Shrivastava, A., Malisiewicz, T., Gupta, A., Efros, A.A.: Data-driven visual similarity for cross-domain image matching. In: Proceedings of the 2011 SIGGRAPH Asia Conference (2011)Google Scholar
  75. 75.
    Singh, S., Gupta, A., Efros, A.A.: Unsupervised discovery of mid-level discriminative patches. In: Proceedings of the European Conference on Computer Vision (2012)Google Scholar
  76. 76.
    Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: CNNs for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  77. 77.
    Szeliski, R.: Image alignment and stitching: a tutorial. Found. Trends. Comput. Graph. Vis. 2, 1–104 (2006)MathSciNetCrossRefGoogle Scholar
  78. 78.
    Thomee, B., et al.: Yfcc100m: the new data in multimedia research. Commun. ACM 59, 64–73 (2016)CrossRefGoogle Scholar
  79. 79.
    Tian, Y., Fan, B., Wu, F.: L2-net: deep learning of discriminative patch descriptor in Euclidean space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  80. 80.
    Ulyanov, D., Vedaldi, A., Lempitsky, V.: Deep image prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  81. 81.
    Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., Murphy, K.: Tracking emerges by colorizing videos. In: Proceedings of the European Conference on Computer Vision (2018)Google Scholar
  82. 82.
    Wang, X., Jabri, A., Efros, A.A.: Learning correspondence from the cycle-consistency of time. In: The IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  83. 83.
    Wang, Y., Yang, Y., Yang, Z., Zhao, L., Wang, P., Xu, W.: Occlusion aware unsupervised learning of optical flow. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  84. 84.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)CrossRefGoogle Scholar
  85. 85.
    Wulff, J., Sevilla-Lara, L., Black, M.J.: Optical flow in mostly rigid scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  86. 86.
    Yin, Z., Shi, J.: Geonet: unsupervised learning of dense depth, optical flow and camera pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  87. 87.
    Zhang, J., et al.: Learning two-view correspondences and geometry using order-aware network. Proceedings of the IEEE International Conference on Computer Vision (2019)Google Scholar
  88. 88.
    Zhang, R.: Making convolutional networks shift-invariant again. In: International Conference on Machine Learning (2019)Google Scholar
  89. 89.
    Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  90. 90.
    Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vis. 127, 302–321 (2018)CrossRefGoogle Scholar
  91. 91.
    Zhou, T., Jae Lee, Y., Yu, S.X., Efros, A.A.: Flowweb: joint image set alignment by weaving consistent, pixel-wise correspondences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  92. 92.
    Zhou, T., Krahenbuhl, P., Aubry, M., Huang, Q., Efros, A.A.: Learning dense correspondence via 3D-guided cycle consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.LIGM (UMR 8049) - Ecole des Ponts, UPEMarne-la-ValléeFrance
  2. 2.Thales Land and Air SystemsBelfastUK
  3. 3.UC BerkeleyBerkeleyUSA

Personalised recommendations