Skip to main content
Springer Nature Link
Log in

Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15100))

Included in the following conference series:

  • 962 Accesses

  • 9 Citations

Abstract

Current feature matching methods prioritize improving modeling capabilities to better align outputs with ground-truth matches, which are the theoretical upper bound on matching results, metaphorically depicted as the “ceiling”. However, these enhancements fail to address the underlying issues that directly hinder ground-truth matches, including the scarcity of matchable points in small scale images, matching conflicts in dense methods, and the keypoint-repeatability reliance in sparse methods. We propose a novel feature matching method named RCM, which Raises the Ceiling of Matching from three aspects. 1) RCM introduces a dynamic view switching mechanism to address the scarcity of matchable points in source images by strategically switching image pairs. 2) RCM proposes a conflict-free coarse matching module, addressing matching conflicts in the target image through a many-to-one matching strategy. 3) By integrating the semi-sparse paradigm and the coarse-to-fine architecture, RCM preserves the benefits of both high efficiency and global search, mitigating the reliance on keypoint repeatability. As a result, RCM enables more matchable points in the source image to be matched in an exhaustive and conflict-free manner in the target image, leading to a substantial 260% increase in ground-truth matches. Comprehensive experiments show that RCM exhibits remarkable performance and efficiency in comparison to state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+
from €37.37 /Month
  • Starting from 10 chapters or articles per month
  • Access and download chapters and articles from more than 300k books and 2,500 journals
  • Cancel anytime
View plans

Buy Now

Chapter
EUR 29.95
Price includes VAT (Netherlands)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
EUR 60.98
Price includes VAT (Netherlands)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
EUR 80.65
Price includes VAT (Netherlands)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

References

  1. Balntas, V., Lenc, K., Vedaldi, A., Mikolajczyk, K.: Hpatches: a benchmark and evaluation of handcrafted and learned local descriptors. In: Proceedings of the CVPR, pp. 5173–5182 (2017)

    Google Scholar 

  2. Barroso-Laguna, A., Tian, Y., Mikolajczyk, K.: Scalenet: a shallow architecture for scale estimation. In: Proceedings of the CVPR, pp. 12808–12818 (2022)

    Google Scholar 

  3. Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006). https://doi.org/10.1007/11744023_32

    Chapter  Google Scholar 

  4. Calonder, M., Lepetit, V., Strecha, C., Fua, P.: BRIEF: binary robust independent elementary features. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 778–792. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_56

    Chapter  Google Scholar 

  5. Chen, H., et al.: Learning to match features with seeded graph matching network. In: Proceedings of the ICCV, pp. 6301–6310 (2021)

    Google Scholar 

  6. Chen, H., et al.: ASpanFormer: detector-free image matching with adaptive span transformer. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. ECCV 2022. LNCS, vol. 13692, pp. 20–36 . Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19824-3_2

  7. Chen, Y., Huang, D., Xu, S., Liu, J., Liu, Y.: Guide local feature matching by overlap estimation. In: Proceedings of the AAAI, pp. 365–373 (2022)

    Google Scholar 

  8. Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the CVPR, pp. 5828–5839 (2017)

    Google Scholar 

  9. DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: Proceedings of the CVPRW, pp. 224–236 (2018)

    Google Scholar 

  10. Dusmanu, M., et al.: D2-Net: a trainable CNN for joint description and detection of local features. In: Proceedings of the CVPR, pp. 8092–8101 (2019)

    Google Scholar 

  11. Edstedt, J., Bökman, G., Wadenbäck, M., Felsberg, M.: Dedode: detect, don’t describe-describe, don’t detect for local feature matching. In: Proceedings of the 3DV, pp. 148–157 (2024)

    Google Scholar 

  12. Edstedt, J., Sun, Q., Bökman, G., Wadenbäck, M., Felsberg, M.: Roma: robust dense feature matching. In: Proceedings of the CVPR, pp. 19790–19800 (2024)

    Google Scholar 

  13. Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. IEEE Trans. Pattern Anal. Mach. Intell. 40(3), 611–625 (2017)

    Article  Google Scholar 

  14. Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 381–395 (1981)

    Google Scholar 

  15. Fu, Y., Wu, Y.: Scale-Net: learning to reduce scale differences for large-scale invariant image matching. arXiv preprint arXiv:2112.10485 (2021)

  16. Germain, H., Bourmaud, G., Lepetit, V.: Sparse-to-dense hypercolumn matching for long-term visual localization. In: Proceedings of the 3DV, pp. 513–523 (2019)

    Google Scholar 

  17. Germain, H., Bourmaud, G., Lepetit, V.: S2DNet: learning image features for accurate sparse-to-dense matching. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 626–643. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_37

    Chapter  Google Scholar 

  18. Gleize, P., Wang, W., Feiszli, M.: Silk: simple learned keypoints. In: Proceedings of the CVPR, pp. 22499–22508 (2023)

    Google Scholar 

  19. Huang, D., et al.: Adaptive assignment for geometry aware local feature matching. In: Proceedings of the CVPR, pp. 5425–5434 (2023)

    Google Scholar 

  20. Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., Yi, K.M.: COTR: correspondence transformer for matching across images. In: Proceedings of the ICCV, pp. 6207–6217 (2021)

    Google Scholar 

  21. Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are rnns: fast autoregressive transformers with linear attention. In: Proceedings of the ICML, pp. 5156–5165 (2020)

    Google Scholar 

  22. Li, X., Han, K., Li, S., Prisacariu, V.: Dual-resolution correspondence networks. In: Proceedings of the NeurIPS, pp. 17346–17357 (2020)

    Google Scholar 

  23. Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: Proceedings of the CVPR, pp. 2041–2050 (2018)

    Google Scholar 

  24. Lindenberger, P., Sarlin, P., Pollefeys, M.: Lightglue: local feature matching at light speed. In: Proceedings of the ICCV, pp. 17627–17638 (2023)

    Google Scholar 

  25. Liu, C., Yuen, J., Torralba, A., Sivic, J., Freeman, W.T.: SIFT flow: dense correspondence across different scenes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5304, pp. 28–42. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88690-7_3

    Chapter  Google Scholar 

  26. Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)

  27. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)

    Article  Google Scholar 

  28. Lu, X., Yan, Y., Kang, B., Du, S.: Paraformer: parallel attention transformer for efficient feature matching. arXiv preprint arXiv:2303.00941 (2023)

  29. Luo, Z., et al.: Aslfeat: learning local features of accurate shape and localization. In: Proceedings of the CVPR, p. 6589 (2020)

    Google Scholar 

  30. Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Proc. NeurIPS 32 (2019)

    Google Scholar 

  31. Revaud, J., De Souza, C., Humenberger, M., Weinzaepfel, P.: R2D2: reliable and repeatable detector and descriptor. In: Proceedings of the NeurIPS, pp. 12414–12424 (2019)

    Google Scholar 

  32. Rocco, I., Arandjelović, R., Sivic, J.: Efficient neighbourhood consensus networks via submanifold sparse convolutions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 605–621. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_35

    Chapter  Google Scholar 

  33. Rocco, I., Cimpoi, M., Arandjelović, R., Torii, A., Pajdla, T., Sivic, J.: Neighbourhood consensus networks. In: Proceedings of the NeurIPS, pp. 1658–1669 (2018)

    Google Scholar 

  34. Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. In: Proceedings of the ICCV, pp. 2564–2571 (2011)

    Google Scholar 

  35. Sarlin, P., Cadena, C.and Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: Proceedings of the CVPR, pp. 12716–12725 (2019)

    Google Scholar 

  36. Sarlin, P., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: Proceedings of the CVPR, pp. 4937–4946 (2020)

    Google Scholar 

  37. Schonberger, J.L., Frahm, J.: Structure-from-motion revisited. In: Proceedings of the CVPR, pp. 4104–4113 (2016)

    Google Scholar 

  38. Shi, Y., Cai, J., Shavit, Y., Mu, T., Feng, W., Zhang, K.: ClusterGNN: cluster-based coarse-to-fine graph neural network for efficient feature matching. In: Proceedings of the CVPR, pp. 12517–12526, June 2022

    Google Scholar 

  39. Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: LoFTR: detector-free local feature matching with transformers. In: Proceedings of the CVPR, pp. 8922–8931 (2021)

    Google Scholar 

  40. Truong, P., Danelljan, M., Timofte, R., Van Gool, L.: PDC-Net+: enhanced probabilistic dense correspondence network. IEEE Trans. Pattern Anal. Mach. Intell. (2023)

    Google Scholar 

  41. Vaswani, A., et al.: Attention is all you need. In: Proceedings of the NeurIPS, pp. 5998–6008 (2017)

    Google Scholar 

  42. Wang, Q., Zhang, J., Yang, K., Peng, K., Stiefelhagen, R.: Matchformer: interleaving attention in transformers for feature matching. In: Proceedings of the ACCV, pp. 2746–2762 (2022)

    Google Scholar 

  43. Wang, Q., Zhou, X., Hariharan, B., Snavely, N.: Learning feature descriptors using camera pose supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 757–774. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_44

    Chapter  Google Scholar 

  44. Zhang, J., et al.: Learning two-view correspondences and geometry using order-aware network. In: Proceedings of the ICCV, pp. 5845–5854 (2019)

    Google Scholar 

  45. Zhang, Z., Sattler, T., Scaramuzza, D.: Reference pose generation for long-term visual localization via learned features and view synthesis. Int. J. Comput. Vis. 821–844 (2021)

    Google Scholar 

  46. Zhao, X., Wu, X., Chen, W., Chen, P.C., Xu, Q., Li, Z.: Aliked: a lighter keypoint and descriptor extraction network via deformable transformation. IEEE Trans. Instrum. Meas. 72, 1–16 (2023)

    Google Scholar 

  47. Zhou, Q., Sattler, T., Leal-Taixe, L.: Patch2pix: epipolar-guided pixel-level correspondences. In: Proceedings of the CVPR, pp. 4669–4678 (2021)

    Google Scholar 

Download references

Acknowledgments

This work was supported by the SEU Innovation Capability Enhancement Plan for Doctoral Students under grant CXJH SEU 24128.

Author information

Authors and Affiliations

  1. School of Automation, Southeast University, Nanjing, China

    Xiaoyong Lu & Songlin Du

Authors
  1. Xiaoyong Lu
    View author publications

    Search author on:PubMed Google Scholar

  2. Songlin Du
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Songlin Du .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Hessen, Germany

    Stefan Roth

  4. Princeton University, Palo Alto, CA, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 51443 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Lu, X., Du, S. (2025). Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15100. Springer, Cham. https://doi.org/10.1007/978-3-031-72946-1_15

Download citation

Keywords

Publish with us

Policies and ethics