4. 4
Abstract
์ด์ ์๋..
Rendering the semantic content of an image in different styles is a difficult image processing task.
์ฌ๋ฌ ๋ค๋ฅธ style image์ content๋ฅผ ๋ ๋๋งํ๋ ๊ฒ์ ์ด๋ ค์ด ์ผ์ด๋ค. ์ฐ๋ฆฌ๋ ์ด๋ ค์ด ์ผ์
ํด๋๋ค!!
Arguably, a major limiting factor for previous approaches has been the lack of image
representations that explicitly represent semantic information and, thus, allow to separate image
content from style.
์ด์ ์๋ ์๋ฏธ ์๋ ์ ๋ณด(contents)๋ฅผ ์ ํํ๊ฒ ํํํ๋ ๊ฒ์ด ๋ถ์กฑํ๋ค. ๊ณ ๋ก,
์คํ์ผ๋ก๋ถํฐ ์ด๋ฏธ์ง ์ปจํ ์ธ ๋ฅผ ๋ถ๋ฆฌํ๊ฒ ๊ฐ๋ฅํ๋ ๊ฒ์ ํ๊ณ๊ฐ ์์๋ค. ์ด๋ค ๋ฐฉ๋ฒ์ ์ผ๊ธธ๋?
5. 5
The algorithm allows us to produce new images of high perceptual quality that combine the
content of an arbitrary photograph with the appearance of numerous well-known artworks.
์ด ์๊ณ ๋ฆฌ์ฆ์ ์ ์๋ ค์ง ์์ ์ํ์ ์คํ์ผ๊ณผ ์์์ ์ฌ์ง์ ์ปจํ ์ธ ๋ฅผ ์กฐํฉํ์ฌ ์๋ก์ด
๊ณ ํ๋ฆฌํฐ์ ์ด๋ฏธ์ง๋ฅผ ๋ง๋ค์ด ๋ธ๋ค.
Our results provide new insights into the deep image representations learned by Convolutional
Neural Networks and demonstrate their potential for high level image synthesis and
manipulation.
์ฐ๋ฆฌ์ ๊ฒฐ๊ณผ๋ฌผ์ CNN์ ์ํ deep image representations์ ๋ํด ์๋ก์ด ์ธ์ธ์ดํธ๋ฅผ ์ ๊ณต
ํ๋ค. ๊ทธ๋ฆฌ๊ณ high level image synthesis & manipulation ์ ๋ํ ํฌํ ์ ์ ์ฆ๋ช ํ๋ค.
Abstract
์ด์ ๋..
6. 6
Introduction
์ด์ ์๋..
Texture transfering์ ์์ ์๋ ์ฌ๋ฌ ๋ฐฉ๋ฒ๋ค์ด ์์๋ค.
์ฃผ๋ก texture transfer algorithm์ ๋ฒ ์ด์ง์ non-parametric methods์๊ณ , ํ๊ฒ ์ด๋ฏธ์ง์
structure์ ๋ณด์กดํ๋ ๋ฐฉ๋ฒ๋ค์ด ๋ฌ๋๋ค.
์๋ฅผ ๋ค๋ฉด,
- Efros&Freeman: correspondence map [link]
- Image Analogies (2001, Hertzman et al) [link]
- Fast Texture Transfer (2001, Ashikhmin) [link]
- Directional Texture Transfer (2010, Lee et al.) [link]
7. 7
Image Quilting for Texture Synthesis and Transfer (2001, Efros & Freeman) [link]
์ผ๊ตด์ ๋ฐฅํ ๋ถ์ด๊ธฐ ๋ผ๋๊ฐ..
์๋ จ โฆ
8. 8
Image Quilting for Texture Synthesis and Transfer (2001, Efros & Freeman) [link]
์ผ๊ตด์ ๋ฐฅํ ๋ถ์ด๊ธฐ ๋ผ๋๊ฐ..
34. 34
LIMITATION 1
Resolution of the synthesized images.
The speed of the synthesis procedure depends heavily on image resolution.
Discussion
35. 35
LIMITATION 2
Noise.
While this is less of an is- sue in the artistic style transfer, the problem becomes more apparent
when both, content and style images, are photographs.
Discussion
41. 41
LIMITATION 2
However, the noise is very characteristic and appears to resemble the filters of units in the
network.
Discussion
42. 42
LIMITATION 3
The separation of image content from style is not necessarily a well defined problem.
This is mostly because it is not clear what exactly defines the style of an image.
It might be the brush strokes in a painting, the colour map, certain dominant forms and shapes,
but also the composition of a scene and the choice of the subject of the image and probably it is
a mixture of all of them and many more.
Discussion
44. 44
LIMITATION 3
In our work we consider style transfer to be successful if the generated image โlooks likeโ the style
image but shows the objects and scenery of the content image.
ํ์ค๊ณผ ํํํ ์๊ฐโฆ
Discussion