Style transfer for headshot portraits
Headshot portraits are a popular subject in photography but to achieve a compelling visual style requires advanced skills that a casual photographer will not have. Further, algorithms that automate or assist the stylization of generic photographs do not perform well on headshots due to the feature-s...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for Computing Machinery (ACM)
2015
|
| Online Access: | http://hdl.handle.net/1721.1/100018 https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0002-2231-7995 |
| _version_ | 1811072928521912320 |
|---|---|
| author | Shih, YiChang Paris, Sylvain Barnes, Connelly Freeman, William T. Durand, Fredo |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Shih, YiChang Paris, Sylvain Barnes, Connelly Freeman, William T. Durand, Fredo |
| author_sort | Shih, YiChang |
| collection | MIT |
| description | Headshot portraits are a popular subject in photography but to achieve a compelling visual style requires advanced skills that a casual photographer will not have. Further, algorithms that automate or assist the stylization of generic photographs do not perform well on headshots due to the feature-specific, local retouching that a professional photographer typically applies to generate such portraits. We introduce a technique to transfer the style of an example headshot photo onto a new one. This can allow one to easily reproduce the look of renowned artists. At the core of our approach is a new multiscale technique to robustly transfer the local statistics of an example portrait onto a new one. This technique matches properties such as the local contrast and the overall lighting direction while being tolerant to the unavoidable differences between the faces of two different people. Additionally, because artists sometimes produce entire headshot collections in a common style, we show how to automatically find a good example to use as a reference for a given portrait, enabling style transfer without the user having to search for a suitable example for each input. We demonstrate our approach on data taken in a controlled environment as well as on a large set of photos downloaded from the Internet. We show that we can successfully handle styles by a variety of different artists. |
| first_indexed | 2024-09-23T09:22:21Z |
| format | Article |
| id | mit-1721.1/100018 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:22:21Z |
| publishDate | 2015 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | dspace |
| spelling | mit-1721.1/1000182022-10-25T05:04:37Z Style transfer for headshot portraits Shih, YiChang Paris, Sylvain Barnes, Connelly Freeman, William T. Durand, Fredo Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Shih, YiChang Freeman, William T. Durand, Fredo Headshot portraits are a popular subject in photography but to achieve a compelling visual style requires advanced skills that a casual photographer will not have. Further, algorithms that automate or assist the stylization of generic photographs do not perform well on headshots due to the feature-specific, local retouching that a professional photographer typically applies to generate such portraits. We introduce a technique to transfer the style of an example headshot photo onto a new one. This can allow one to easily reproduce the look of renowned artists. At the core of our approach is a new multiscale technique to robustly transfer the local statistics of an example portrait onto a new one. This technique matches properties such as the local contrast and the overall lighting direction while being tolerant to the unavoidable differences between the faces of two different people. Additionally, because artists sometimes produce entire headshot collections in a common style, we show how to automatically find a good example to use as a reference for a given portrait, enabling style transfer without the user having to search for a suitable example for each input. We demonstrate our approach on data taken in a controlled environment as well as on a large set of photos downloaded from the Internet. We show that we can successfully handle styles by a variety of different artists. Quanta Computer (Firm) Adobe Systems 2015-11-24T13:43:18Z 2015-11-24T13:43:18Z 2014-07 Article http://purl.org/eprint/type/ConferencePaper 07300301 http://hdl.handle.net/1721.1/100018 YiChang Shih, Sylvain Paris, Connelly Barnes, William T. Freeman, and Fredo Durand. 2014. Style transfer for headshot portraits. ACM Trans. Graph. 33, 4, Article 148 (July 2014), 14 pages. https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0002-2231-7995 en_US http://dx.doi.org/10.1145/2601097.2601137 ACM Transactions on Graphics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery (ACM) MIT web domain |
| spellingShingle | Shih, YiChang Paris, Sylvain Barnes, Connelly Freeman, William T. Durand, Fredo Style transfer for headshot portraits |
| title | Style transfer for headshot portraits |
| title_full | Style transfer for headshot portraits |
| title_fullStr | Style transfer for headshot portraits |
| title_full_unstemmed | Style transfer for headshot portraits |
| title_short | Style transfer for headshot portraits |
| title_sort | style transfer for headshot portraits |
| url | http://hdl.handle.net/1721.1/100018 https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0002-2231-7995 |
| work_keys_str_mv | AT shihyichang styletransferforheadshotportraits AT parissylvain styletransferforheadshotportraits AT barnesconnelly styletransferforheadshotportraits AT freemanwilliamt styletransferforheadshotportraits AT durandfredo styletransferforheadshotportraits |