HSCNet++ : Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer

Shuzhe Wang, Zakaria Laskar, Iaroslav Melekhov, Xiaotian Li, Yi Zhao, Giorgos Tolias, Juho Kannala

Tutkimustuotos: LehtiartikkeliArticleScientificvertaisarvioitu

1 Sitaatiot (Scopus)

Abstrakti

Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model. Recently, deep neural networks have been exploited to regress the mapping between raw pixels and 3D coordinates in the scene, and thus the matching is implicitly performed by the forward pass through the network. However, in a large and ambiguous environment, learning such a regression task directly can be difficult for a single network. In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image. The proposed method, which is an extension of HSCNet, allows us to train compact models which scale robustly to large environments. It sets a new state-of-the-art for single-image localization on the 7-Scenes, 12-Scenes, Cambridge Landmarks datasets, and the combined indoor scenes.
AlkuperäiskieliEnglanti
Sivumäärä21
JulkaisuINTERNATIONAL JOURNAL OF COMPUTER VISION
DOI - pysyväislinkit
TilaSähköinen julkaisu (e-pub) ennen painettua julkistusta - 6 helmik. 2024
OKM-julkaisutyyppiA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Sormenjälki

Sukella tutkimusaiheisiin 'HSCNet++ : Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä