[Theory] REMINDER: 7/12 Thesis Defense: Nicholas Kolkin, TTIC

[Mary Marre]

*Thesis Defense: Nicholas Kolkin, TTIC*

*When:  *     Monday*,* July 12th at *9:00 - 11:00 am CT*



*Where:*      TTIC, 6045 S. Kenwood Avenue, 5th floor, Room 530


*Note:*         There will be *limited in-person attendance for fully
vaccinated persons*.
*For members of TTIC community: *if you would like to attend, please sign
up specifically in the "Nick's defense" section at the bottom of the July
12 column in the TTIC spreadsheet, by adding your name and entering "1".
You can do so as long as capacity does not exceed 15. Please only sign up
in that section (and do not also mark "1" in the normal row for your name)
to keep the total in-person count correct.
*https://docs.google.com/spreadsheets/d/1riLfzATcp6NDH0mReGZxpvevfc6Yi2apJ-Ye4uZU62A/edit#gid=1351650168*
<https://docs.google.com/spreadsheets/d/1riLfzATcp6NDH0mReGZxpvevfc6Yi2apJ-Ye4uZU62A/edit#gid=1351650168>
*For people outside TTIC:* if you are interested to attend please contact
Greg Shakhnarovich, greg at ttic.edu.



*Virtually: *  *Register in advance here
<https://uchicagogroup.zoom.us/webinar/register/WN_l4Hez5bZQKmjtjL2ZSbRtQ>*



*Who: *        Nicholas Kolkin, TTIC


*Title:        *Non-Parametric Neural Style Transfer

*Abstract:  *It seems easy to imagine a photograph of the Eiffel Tower
painted in the style of Vincent van Gogh's 'The Starry Night', but upon
introspection it is difficult to precisely define what this would entail.
What visual elements must an image contain to represent the 'content' of
the Eiffel Tower? What visual elements of 'The Starry Night' are caused by
van Gogh's 'style' rather than his decision to depict a village under the
night sky? Precisely defining 'content' and 'style' is a central challenge
of designing algorithms for artistic style transfer, algorithms which can
recreate photographs using an artwork's style. My efforts defining these
terms, and designing style transfer algorithms themselves, are the focus of
this thesis. I will begin by proposing novel definitions of style and
content based on optimal transport and self-similarity, and demonstrating
how a style transfer algorithm based on these definitions generates outputs
with improved visual quality. Then I will describe how the traditional
texture-based definition of style can be expanded to include elements of
geometry and proportion by jointly optimizing a keypoint-guided deformation
field alongside the stylized output's pixels. Finally I will describe a
framework inspired by both modern neural style transfer algorithms and
traditional patch-based synthesis approaches which is fast, general, and
offers state-of-the-art visual quality.


*Thesis Advisor:* *Greg Shakhnarovich* <greg at ttic.edu>



Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Chicago, IL  60637*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Tue, Jun 29, 2021 at 11:38 AM Mary Marre <mmarre at ttic.edu> wrote:

> *Thesis Defense: Nicholas Kolkin, TTIC*
>
> *When:  *     Monday*,* July 12th at *9:00 - 11:00 am CT*
>
>
>
> *Where:*      TTIC, 6045 S. Kenwood Avenue, 5th floor, Room 530
>
>
> *Note:*         In person attendance will be limited and require sign up.
> More details to follow.
>
>
>
> *Virtually: *  *Register in advance here
> <https://uchicagogroup.zoom.us/webinar/register/WN_l4Hez5bZQKmjtjL2ZSbRtQ>*
>
>
>
> *Who: *       Nicholas Kolkin, TTIC
>
>
> *Title:        *Non-Parametric Neural Style Transfer
>
> *Abstract:  *It seems easy to imagine a photograph of the Eiffel Tower
> painted in the style of Vincent van Gogh's 'The Starry Night', but upon
> introspection it is difficult to precisely define what this would entail.
> What visual elements must an image contain to represent the 'content' of
> the Eiffel Tower? What visual elements of 'The Starry Night' are caused by
> van Gogh's 'style' rather than his decision to depict a village under the
> night sky? Precisely defining 'content' and 'style' is a central challenge
> of designing algorithms for artistic style transfer, algorithms which can
> recreate photographs using an artwork's style. My efforts defining these
> terms, and designing style transfer algorithms themselves, are the focus of
> this thesis. I will begin by proposing novel definitions of style and
> content based on optimal transport and self-similarity, and demonstrating
> how a style transfer algorithm based on these definitions generates outputs
> with improved visual quality. Then I will describe how the traditional
> texture-based definition of style can be expanded to include elements of
> geometry and proportion by jointly optimizing a keypoint-guided deformation
> field alongside the stylized output's pixels. Finally I will describe a
> framework inspired by both modern neural style transfer algorithms and
> traditional patch-based synthesis approaches which is fast, general, and
> offers state-of-the-art visual quality.
>
>
> *Thesis Advisor:* *Greg Shakhnarovich* <greg at ttic.edu>
>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Chicago, IL  60637*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20210707/f73c28d0/attachment.html>