Example-based super-resolution
William T. Freeman, Thouis R. Jones, Egon C. Pasztor · IEEE Computer Graphics and Applications · 2002
We call methods for achieving high-resolution enlargements of pixel-based images super-resolution algorithms. Many applications in graphics or image processing could benefit from such resolution independence, including image-based rendering (IBR), texture mapping, enlarging consumer photographs, and converting NTSC video content to high-definition television. We built on another training-based super-resolution algorithm and developed a faster and simpler algorithm for one-pass super-resolution. Our algorithm requires only a nearest-neighbor search in the training set for a vector derived from each patch of local image data. This one-pass super-resolution algorithm is a step toward achieving resolution independence in image-based representations. We don't expect perfect resolution independence-even the polygon representation doesn't have that-but increasing the resolution independence of pixel-based representations is an important task for IBR.
Cited by 2,498 works. doi:10.1109/38.988747
Authors
References
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
- Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
- What Is the Goal of Sensory Coding?
- Learning Low-Level Vision
- Cubic convolution interpolation for digital image processing
- Image quilting for texture synthesis and transfer
- Image analogies
- Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms
- Limits on super-resolution and how to break them
- Generalized Belief Propagation