Constrained patchmatch for image completion

Guillaume Chican 1 Mohamed Tamaazousti 1
1 LVIC - Laboratoire Vision et Ingénierie des Contenus
DIASI - Département Intelligence Ambiante et Systèmes Interactifs : DRT/LIST/DIASI
Abstract : We propose a quick and automatic patch-based image completion method, which uses the PatchMatch framework. We show that PatchMatch can be improved by constraining its random search step, in order to propagate the geometric structures of the image better. Instead of randomly initializing the algorithm and randomly searching, we guide the search by constraining it among only the most likely offsets. Moreover we modify the PatchMatch cost function to ensure a coherence of offset directions. The method is tested with real data, and is compared with state-of-the-art methods
Complete list of metadatas

https://hal-cea.archives-ouvertes.fr/cea-01836543
Contributor : Vincent Gay-Bellile <>
Submitted on : Thursday, July 12, 2018 - 1:42:11 PM
Last modification on : Wednesday, January 23, 2019 - 2:39:23 PM

Identifiers

  • HAL Id : cea-01836543, version 1

Collections

CEA | DRT | LIST

Citation

Guillaume Chican, Mohamed Tamaazousti. Constrained patchmatch for image completion. International Symposium on Visual Computing , Aug 2014, las Vegas, United States. ⟨cea-01836543⟩

Share

Metrics

Record views

57