SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches

Rémi Giraud (1, 2) , Vinh-Thong Ta (3, 1) , Aurélie Bugeau (1) , Pierrick Coupé (1) , Nicolas Papadakis (2)

1 LaBRI - Laboratoire Bordelais de Recherche en Informatique
2 IMB - Institut de Mathématiques de Bordeaux
3 Bordeaux INP - Institut Polytechnique de Bordeaux

Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the image content. In this paper, we first introduce a novel structure, a superpixel-based patch, called SuperPatch. The proposed structure, based on superpixel neighborhood, leads to a robust descriptor since spatial information is naturally included. The generalization of the PatchMatch method to SuperPatches, named SuperPatchMatch, is introduced. Finally, we propose a framework to perform fast segmentation and labeling from an image database, and demonstrate the potential of our approach since we outperform, in terms of computational cost and accuracy, the results of state-of-the-art methods on both face labeling and medical image segmentation.

Mots clés: Patch-based method; PatchMatch; Labeling; Superpixels; Segmentation

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Imagerie médicale; Traitement des images [eess.IV]

Rémi Giraud, Vinh-Thong Ta, Aurélie Bugeau, Pierrick Coupé, Nicolas Papadakis. SuperPatchMatch: an Algorithm for Robust Correspondences using Superpixel Patches. IEEE Transactions on Image Processing, 2017, ⟨10.1109/TIP.2017.2708504⟩. ⟨hal-01432116⟩