Guiding Local Feature Matching with Surface Curvature

Shuzhe Wang, Juho Kannala, Daniel Barath, Marc Pollefeys

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

15 Downloads (Pure)


We propose a new method, called curvature similar- ity extractor (CSE), for improving local feature matching across images. CSE calculates the curvature of the local 3D surface patch for each detected feature point in a viewpoint- invariant manner via fitting quadrics to predicted monocu- lar depth maps. This curvature is then leveraged as an addi- tional signal in feature matching with off-the-shelf matchers like SuperGlue and LoFTR. Additionally, CSE enables end- to-end joint training by connecting the matcher and depth predictor networks. Our experiments demonstrate on large- scale real-world datasets that CSE consistently improves the accuracy of state-of-the-art methods. Fine-tuning the depth prediction network further enhances the accuracy. The proposed approach achieves state-of-the-art results on the ScanNet dataset, showcasing the effectiveness of incor- porating 3D geometric information into feature matching.
Original languageEnglish
Title of host publication2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Number of pages10
ISBN (Electronic)979-8-3503-0718-4
ISBN (Print)979-8-3503-0719-1
Publication statusPublished - 2023
MoE publication typeA4 Conference publication
EventInternational Conference on Computer Vision - Paris, France
Duration: 1 Oct 20236 Oct 2023

Publication series

NameIEEE International Conference on Computer Vision
ISSN (Print)1550-5499
ISSN (Electronic)2380-7504


ConferenceInternational Conference on Computer Vision
Abbreviated titleICCV


Dive into the research topics of 'Guiding Local Feature Matching with Surface Curvature'. Together they form a unique fingerprint.

Cite this