Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features

Résumé

Establishing visual correspondences under large intra-class variations requires analyzing images at different levels , from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by "hyper-pixels" that leverage a small number of relevant features selected among early to late layers of a convolutional neu-ral network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.
Fichier principal
Vignette du fichier
5417.pdf (2.17 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02267044 , version 1 (18-08-2019)

Identifiants

  • HAL Id : hal-02267044 , version 1

Citer

Juhong Min, Jongmin Lee, Jean Ponce, Minsu Cho. Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features. ICCV 2019 - International Conference on Computer Vision, Oct 2019, Seoul, South Korea. ⟨hal-02267044⟩
118 Consultations
57 Téléchargements

Partager

Gmail Facebook X LinkedIn More