Graphcut textures
Vivek Kwatra, Arno Schödl, Irfan A. Essa et al. · ACM SIGGRAPH Conference Papers (SIGGRAPH) · 2003
In this paper we introduce a new algorithm for image and video texture synthesis. In our approach, patch regions from a sample image or video are transformed and copied to the output and then stitched together along optimal seams to generate a new (and typically larger) output. In contrast to other techniques, the size of the patch is not chosen a-priori, but instead a graph cut technique is used to determine the optimal patch region for any given offset between the input and output texture. Unlike dynamic programming, our graph cut technique for seam optimization is applicable in any dimension. We specifically explore it in 2D and 3D to perform video texture synthesis in addition to regular image synthesis. We present approximative offset search techniques that work well in conjunction with the presented patch size optimization. We show results for synthesizing regular, random, and natural images and videos. We also demonstrate how this method can be used to interactively merge different images to generate new scenes.
Cited by 1,216 works. doi:10.1145/1201775.882264
Authors
References
- Flows in networks
- Texture synthesis by non-parametric sampling
- Summed-area tables for texture mapping
- Pyramid-based texture analysis/synthesis
- Image quilting for texture synthesis and transfer
- Exact Maximum A Posteriori Estimation for Binary Images
- A multiresolution spline with application to image mosaics
- A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
- Multiresolution sampling procedure for analysis and synthesis of texture images
- Fast texture synthesis using tree-structured vector quantization