Fast texture synthesis using tree-structured vector quantization
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
Real-time texture synthesis by patch-based sampling
ACM Transactions on Graphics (TOG)
Synthesis of bidirectional texture functions on arbitrary surfaces
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Towards real-time texture synthesis with the jump map
EGRW '02 Proceedings of the 13th Eurographics workshop on Rendering
Texture Synthesis by Non-Parametric Sampling
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Graphcut textures: image and video synthesis using graph cuts
ACM SIGGRAPH 2003 Papers
Wang Tiles for image and texture generation
ACM SIGGRAPH 2003 Papers
Feature matching and deformation for texture synthesis
ACM SIGGRAPH 2004 Papers
Jump map-based interactive texture synthesis
ACM Transactions on Graphics (TOG)
Parallel controllable texture synthesis
ACM SIGGRAPH 2005 Papers
Texture optimization for example-based synthesis
ACM SIGGRAPH 2005 Papers
Optimizing the parameters for patch-based texture synthesis
Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications
Appearance-space texture synthesis
ACM SIGGRAPH 2006 Papers
Tile-based texture mapping on graphics hardware
SIGGRAPH '04 ACM SIGGRAPH 2004 Sketches
ACM SIGGRAPH 2008 papers
Accelerated parallel texture optimization
Journal of Computer Science and Technology
Efficient texture synthesis using strict Wang Tiles
Graphical Models
| Hi-index | 0.00 |
This paper presents a novel parallel algorithm to synthesize textures in patches. It decomposes the synthesis process into two steps by the chessboard pattern, with the first step to place patches in the black grids, and the second step to select suitable patches to fill the white grids, where a grid is in the same size of a patch. This way the placed patches in the first step have very weak constraints between them, and in the second step the selected patches are only dependent on their respective surrounding patches, according to the popularly used MRF model to guide texture synthesis. Thus, our proposed algorithm can run in parallel without a hierarchical structure and iterative computation that are always expensive and required in existing parallel synthesis algorithms. At the same time, we adopt a measure to generate patches that can well reflect the periodic feature variation in the sample texture, so as to have texture features transited consistently between neighboring patches for high-quality synthesis. The results show that our proposed algorithm greatly promotes texture synthesis, being able to real time produce large textures in high quality, e.g., generating a texture in 2048*2048 pixels at over 55 fps on a common personnel computer.