Proceedings of the 27th annual conference on Computer graphics and interactive techniques
I3D '01 Proceedings of the 2001 symposium on Interactive 3D graphics
Image quilting for texture synthesis and transfer
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Graphcut textures: image and video synthesis using graph cuts
ACM SIGGRAPH 2003 Papers
Feature matching and deformation for texture synthesis
ACM SIGGRAPH 2004 Papers
Parallel controllable texture synthesis
ACM SIGGRAPH 2005 Papers
Texture design using a simplicial complex of morphable textures
ACM SIGGRAPH 2005 Papers
Eliminating Structure and Intensity Misalignment in Image Stitching
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Appearance-space texture synthesis
ACM SIGGRAPH 2006 Papers
ACM SIGGRAPH 2006 Papers
PatchMatch: a randomized correspondence algorithm for structural image editing
ACM SIGGRAPH 2009 papers
Depth from edge and intensity based stereo
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Stylizing animation by example
ACM Transactions on Graphics (TOG) - SIGGRAPH 2013 Conference Proceedings
PatchNet: a patch-based image representation for interactive library-driven image editing
ACM Transactions on Graphics (TOG)
| Hi-index | 0.00 |
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.