In our last monthly student seminar we were happy to host Tamar Rott Shaham, a PhD student from the Electrical Engineering department at the Technion and IMVC 2017 winner of the students competition. Tamar’s supervisor is Prof. Tomer Michaeli.
Tamar’s presented her research on Visualizing Image Priors.
Image priors play a key role in low-level vision tasks. Different priors capture different geometric properties. Nevertheless, there is currently no unified approach to interpreting and comparing priors of different nature. In her talk, Tamar introduced a simple technique for visualizing image priors where it is determined how images should be deformed so as to best conform to a given image model. The deformed images constructed this way, highlight the elementary geometric structures to which the prior resonates.
Tamar demonstrated how to use their approach to study various popular image models, and reveal interesting behaviors, which were not noticed in the past.
Finally, Tamar presented denoising experiments that validate that the structures revealed as ‘optimal’ for a specific prior are indeed better denoised by this prior.
For Tamar Rott Shaham’s presentation click here
You understand that when using the Site you may be exposed to content from a variety of sources, and that SagivTech is not responsible for the accuracy, usefulness, safety or intellectual property rights of, or relating to, such content and that such content does not express SagivTech’s opinion or endorsement of any subject matter and should not be relied upon as such. SagivTech and its affiliates accept no responsibility for any consequences whatsoever arising from use of such content. You acknowledge that any use of the content is at your own risk.