Higher-order MRFs based image super resolution: why not MAP?
This work addresses computational efficiency in image super-resolution for applications requiring fast processing, but it is incremental as it focuses on optimizing inference methods within an existing prior framework.
The paper tackles the single image super-resolution problem using a higher-order Markov Random Fields prior, showing that maximum a posteriori (MAP) inference is computationally efficient and performs equally well or better than minimum mean square error (MMSE) estimates, with practical experiments demonstrating comparable or improved results.
A trainable filter-based higher-order Markov Random Fields (MRFs) model - the so called Fields of Experts (FoE), has proved a highly effective image prior model for many classic image restoration problems. Generally, two options are available to incorporate the learned FoE prior in the inference procedure: (1) sampling-based minimum mean square error (MMSE) estimate, and (2) energy minimization-based maximum a posteriori (MAP) estimate. This letter is devoted to the FoE prior based single image super resolution (SR) problem, and we suggest to make use of the MAP estimate for inference based on two facts: (I) It is well-known that the MAP inference has a remarkable advantage of high computational efficiency, while the sampling-based MMSE estimate is very time consuming. (II) Practical SR experiment results demonstrate that the MAP estimate works equally well compared to the MMSE estimate with exactly the same FoE prior model. Moreover, it can lead to even further improvements by incorporating our discriminatively trained FoE prior model. In summary, we hold that for higher-order natural image prior based SR problem, it is better to employ the MAP estimate for inference.