Vardan Papyan, M.Sc. Thesis Seminar
Many image restoration algorithms in recent years are based on patch-processing. The core idea is to decompose the target image into fully overlapping patches, restore each of them separately, and then merge the results somehow. This concept has been demonstrated to be highly effective, leading often times to state-of-the-art results in denoising, deblurring, super-resolution, and other applications. Several questions arise from this line of work:
1) How can the local model be enforced on patches extracted from the final outcome?
2) Can we keep a local treatment while getting a near-optimal global service to the inverse problem at hand?
3) What is the global model corresponding to the local prior? And
4) Can we propose a theoretical backbone for the use of the local model in characterizing the global unknown image?
These questions and their answers will be the topic of our talk.