Stylized Depiction of Images Based on Depth Perception


Jorge Lopez-Moreno
Universidad de Zaragoza
Jorge Jimenez
Universidad de Zaragoza
Sunil Hadap
Adobe Systems Inc
Erik Reinhard
University of Bristol
Ken Anjyo
OLM Digital Inc
Diego Gutierrez
Universidad de Zaragoza

NPAR: Non-Photorealistic Animation and Rendering 2010 BEST PAPER AWARD

teaser


Abstract:
Recent works in image editing are opening up new possibilities to manipulate and enhance input images. Within this context, we leverage well-known characteristics of human perception along with a simple depth approximation algorithm to creatively relight images for the purpose of generating non-photorealistic renditions that would be difficult to achieve with existing methods. Our real-time implementation on graphics hardware allows the user to efficiently explore artistic possibilities for each image. We show results produced with four different styles proving the versatility of our approach, and validate our assumptions and simplifications by means of a user study.


News: Our work received the best paper award and was chosen for the front cover in the NPAR proceedings [photo].

 

Direct Links:
[Paper][Slides (24 MB)] [Video 1 (26.9MB)][Video 2 (38.7MB)][Extended Project]

BibTeX:
@inproceedings{ Lopez-Moreno10c,
author = "Jorge Lopez-Moreno and Jorge Jimenez and Sunil Hadap and Erik Reinhard and Ken Anjyo and Diego Gutierrez",
title = "Stylized Depiction of Images Based on Depth Perception",
booktitle = "NPAR '10: Proceedings of the 8th international symposium on Non-photorrealistic animation and rendering",
year = "2010",
location = "Annecy, France",
publisher = "ACM" }