Constrained patchmatch for image completion - Archive ouverte HAL Access content directly
Conference Papers Year :

Constrained patchmatch for image completion

(1) , (1)
1

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
Not file

Dates and versions

cea-01836543 , version 1 (12-07-2018)

Identifiers

  • HAL Id : cea-01836543 , version 1

Cite

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

Collections

CEA DRT LIST
58 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More