Skip to Main content Skip to Navigation
Conference papers

Parallel Patch-based Texture Synthesis

Anass Lasram 1 Sylvain Lefebvre 1 
1 ALICE - Geometry and Lighting
Inria Nancy - Grand Est, LORIA - ALGO - Department of Algorithms, Computation, Image and Geometry
Abstract : Fast parallel algorithms exist for pixel-based texture synthesizers. Unfortunately, these synthesizers often fail to preserve structures from the exemplar without the user specifying additional feature information. On the contrary, patch-based synthesizers are better at capturing and preserving structural patterns. However, they require relatively slow algorithms to layout the patches and stitch them together. We present a parallel patch-based texture synthesis technique that achieves high degree of parallelism. Our synthesizer starts from a low-quality result and adds several patches in parallel to improve it. It selects patches that blend in a seamless way with the existing result, and that hide existing visual artifacts. This is made possible through two main algorithmic contributions: An algorithm to quickly find a good cut around a patch, and a deformation algorithm to further align features crossing the patch boundary. We show that even with a uniform parallel random sampling of the patches, our improved patch stitching achieves high quality synthesis results. We discuss several synthesis strategies, such as using patches of decreasing size or using various amounts of deformation during the optimization. We propose a complete implementation tuned to take advantage of massive GPU parallelism.
Document type :
Conference papers
Complete list of metadata
Contributor : Sylvain Lefebvre Connect in order to contact the contributor
Submitted on : Monday, November 5, 2012 - 2:26:26 PM
Last modification on : Saturday, October 16, 2021 - 11:26:07 AM




Anass Lasram, Sylvain Lefebvre. Parallel Patch-based Texture Synthesis. Eurographics/ ACM SIGGRAPH Symposium on High Performance Graphics, Jun 2013, Paris, France. pp.115-124, ⟨10.2312/EGGH/HPG12/115-124⟩. ⟨hal-00748535⟩



Record views