Image stylisation: from predefined to personalised
The authors present a framework for interactive design of new image stylisations using a wide range of predefined filter blocks. Both novel and off‐the‐shelf image filtering and rendering techniques are extended and combined to allow the user to unleash their creativity to intuitively invent, modify...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-09-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2019.0787 |
| _version_ | 1797684718840315904 |
|---|---|
| author | Ignacio Garcia‐Dorado Pascal Getreuer Bartlomiej Wronski Peyman Milanfar |
| author_facet | Ignacio Garcia‐Dorado Pascal Getreuer Bartlomiej Wronski Peyman Milanfar |
| author_sort | Ignacio Garcia‐Dorado |
| collection | DOAJ |
| description | The authors present a framework for interactive design of new image stylisations using a wide range of predefined filter blocks. Both novel and off‐the‐shelf image filtering and rendering techniques are extended and combined to allow the user to unleash their creativity to intuitively invent, modify, and tune new styles from a given set of filters. In parallel to this manual design, they propose a novel procedural approach that automatically assembles sequences of filters, leading to unique and novel styles. An important aim of the authors’ framework is to allow for interactive exploration and design, as well as to enable videos and camera streams to be stylised on the fly. In order to achieve this real‐time performance, they use the Best Linear Adaptive Enhancement (BLADE) framework – an interpretable shallow machine learning method that simulates complex filter blocks in real time. Their representative results include over a dozen styles designed using their interactive tool, a set of styles created procedurally, and new filters trained with their BLADE approach. |
| first_indexed | 2024-03-12T00:33:48Z |
| format | Article |
| id | doaj.art-0aabfbddd4a247188e013123123b708a |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:33:48Z |
| publishDate | 2020-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-0aabfbddd4a247188e013123123b708a2023-09-15T10:06:49ZengWileyIET Computer Vision1751-96321751-96402020-09-0114629130310.1049/iet-cvi.2019.0787Image stylisation: from predefined to personalisedIgnacio Garcia‐Dorado0Pascal Getreuer1Bartlomiej Wronski2Peyman Milanfar3Google Research1600 Amphitheater ParkwayMountain ViewCA94043USAGoogle Research1600 Amphitheater ParkwayMountain ViewCA94043USAGoogle Research1600 Amphitheater ParkwayMountain ViewCA94043USAGoogle Research1600 Amphitheater ParkwayMountain ViewCA94043USAThe authors present a framework for interactive design of new image stylisations using a wide range of predefined filter blocks. Both novel and off‐the‐shelf image filtering and rendering techniques are extended and combined to allow the user to unleash their creativity to intuitively invent, modify, and tune new styles from a given set of filters. In parallel to this manual design, they propose a novel procedural approach that automatically assembles sequences of filters, leading to unique and novel styles. An important aim of the authors’ framework is to allow for interactive exploration and design, as well as to enable videos and camera streams to be stylised on the fly. In order to achieve this real‐time performance, they use the Best Linear Adaptive Enhancement (BLADE) framework – an interpretable shallow machine learning method that simulates complex filter blocks in real time. Their representative results include over a dozen styles designed using their interactive tool, a set of styles created procedurally, and new filters trained with their BLADE approach.https://doi.org/10.1049/iet-cvi.2019.0787image stylisationinteractive designpredefined filter blocksoff‐the‐shelf image filteringrendering techniquesmanual design |
| spellingShingle | Ignacio Garcia‐Dorado Pascal Getreuer Bartlomiej Wronski Peyman Milanfar Image stylisation: from predefined to personalised IET Computer Vision image stylisation interactive design predefined filter blocks off‐the‐shelf image filtering rendering techniques manual design |
| title | Image stylisation: from predefined to personalised |
| title_full | Image stylisation: from predefined to personalised |
| title_fullStr | Image stylisation: from predefined to personalised |
| title_full_unstemmed | Image stylisation: from predefined to personalised |
| title_short | Image stylisation: from predefined to personalised |
| title_sort | image stylisation from predefined to personalised |
| topic | image stylisation interactive design predefined filter blocks off‐the‐shelf image filtering rendering techniques manual design |
| url | https://doi.org/10.1049/iet-cvi.2019.0787 |
| work_keys_str_mv | AT ignaciogarciadorado imagestylisationfrompredefinedtopersonalised AT pascalgetreuer imagestylisationfrompredefinedtopersonalised AT bartlomiejwronski imagestylisationfrompredefinedtopersonalised AT peymanmilanfar imagestylisationfrompredefinedtopersonalised |