Workshop on Photographic Aesthetics and Non-Photorealistic Rendering (PAESNPR13)

held at PSIVT, Guanajuato, Mexico

28 October 2013

Guanajuato, using the Van Gogh effect by Lara Ruffolo

Program

Keynote talk: "Image Color Transfer with Naturalness Constraints", Dr. Xuemei Zhang (slides)

Abstract

In consumer imaging applications involving photo collages or composition of user photos with professional artwork, inconsistent color appearance of photos and artwork from different sources can result in compositions that do not look aesthetically pleasing.  Users often express a desire to modify individual images to achieve a more consistent color appearance.  Prior work in color transfer that extracted the color properties of one image and applied it to another has shown very interesting results.   Those works focused on achieving an artistic effect, usually without the constraint of conserving object color.   In consumer imaging, we have to be more conscious about conserving general object color and especially skin tones, which are not amenable to aggressive color change.   In this talk I will describe an algorithm to estimate the color and tone properties of an image and transfer these properties to another image under a strong naturalness constraint.  With this method, color changes are constrained to correspond to incomplete adaptation under natural illuminants.  We use a simple Bayesian method to characterize scene color properties, expressed as scene color temperature and illumination levels.  An existing color adaptation model RLAB is used to apply color changes by simulating incomplete adaptation to a target illuminant.  We emphasize that this is not a method of white point estimation nor a white balance  procedure.  Rather, we use color adaptation models as a means to ensure color adjustments to be “plausible”, and therefore maintain a natural appearance to the images even after significant color adjustments.

Speaker

Xuemei Zhang has worked as an imaging scientist/architect at HP Labs, Agilent Labs, Micron Technology, and currently at Apple. She received her BS in psychology from Beijing University and her Masters in statistics and PhD in psychology from Stanford University.  Her work has focused on imaging algorithms for cameras and displays, as well as color image quality metrics.  This talk reviews work on color transfer she did (in collaboration with Hui Chao and Daniel Tretter) while she was a senior research scientist at HP Labs.


+ 3 papers presented as below

"Animated Non-Photorealistic Rendering in Multiple Styles", 
by Ting-Yen Chen, Reinhard Klette (U. Auckland) (slides)

"Rating Image Aesthetics Using a Crowd-Sourcing Approach", 
by Abhishek Agrawal, Vittal Premachandran, Ramakrishna Kakarala (NTU) (slides)

"Inverse skeletal strokes" 
by Dongwei Liu, Reinhard Klette (U. Auckland) (slides)
 


Purpose of workshop
Along with the ubiquity of digital imagery, there is considerable interest in analysing images to measure their aesthetic properties as well as processing them to enhance their visual appeal. The interest in measuring and enhancing visual appeal is motivated by the needs of camera manufacturers, photographic enhancement software suppliers, printer manufacturers, and photo-sharing services to increase user satisfaction. Research has emerged recently which applies computer vision, computer graphics and machine learning both to understand the statistical nature of visual appeal and to improve it. Non-photorealistic rendering (NPR) combines computer graphics and computer vision to produce renderings in various artistic or stylised ways and, beyond increasing appeal, has many possible applications, such as augmented environments, videoconferencing, post-production of films, computer games, interactive TV, education and training, video-based consumer electronics and scientific imaging. This workshop will provide an opportunity for researchers working in measuring and enhancing visual appeal to meet and discuss their ideas in a collegial and interactive format. Papers are invited on relevant topics including, but not limited to, the following:
  1. What constitutes style in photography, and can it be learned through computer vision techniques?
  2. What do expert photographers see that amateurs do not when composing a picture? Can computer vision and behavioral studies (eye-tracking) tell us?
  3. How do aesthetic considerations affect the design of image pipeline algorithms used in digital cameras?
  4. Nonphotorealistic rendering from images or video
  5. Expressive rendering
  6. Style transfer
  7. Visual composition

We encourage participation from researchers with either quantitative (computer science, engineering, mathematical) or qualitative (artistic, art history, art theory) approaches.



 

 
Endorsed by                                          Published in
 
 

Updated 24 May 2013