Guiding Local Feature Matching with Surface Curvature

Shuzhe Wang, Juho Kannala, Daniel Barath, Marc Pollefeys

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

23 Lataukset (Pure)

Abstrakti

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.
AlkuperäiskieliEnglanti
Otsikko2023 IEEE/CVF International Conference on Computer Vision (ICCV)
KustantajaIEEE
Sivut17981-17991
Sivumäärä10
ISBN (elektroninen)979-8-3503-0718-4
ISBN (painettu)979-8-3503-0719-1
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Computer Vision - Paris, Ranska
Kesto: 1 lokak. 20236 lokak. 2023

Julkaisusarja

NimiIEEE International Conference on Computer Vision
KustantajaIEEE
ISSN (painettu)1550-5499
ISSN (elektroninen)2380-7504

Conference

ConferenceInternational Conference on Computer Vision
LyhennettäICCV
Maa/AlueRanska
KaupunkiParis
Ajanjakso01/10/202306/10/2023

Sormenjälki

Sukella tutkimusaiheisiin 'Guiding Local Feature Matching with Surface Curvature'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä