Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations
IEEE Transactions on Pattern Analysis and Machine Intelligence
Gradient domain high dynamic range compression
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
ACM SIGGRAPH 2003 Papers
Learning a Classification Model for Segmentation
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
ACM SIGGRAPH 2006 Papers
Image fusion for context enhancement and video surrealism
SIGGRAPH '05 ACM SIGGRAPH 2005 Courses
Image and depth from a conventional camera with a coded aperture
ACM SIGGRAPH 2007 papers
Real-time gradient-domain painting
ACM SIGGRAPH 2008 papers
ACM SIGGRAPH 2009 papers
Natural and seamless image composition with color control
IEEE Transactions on Image Processing
GradientShop: A gradient-domain optimization framework for image and video filtering
ACM Transactions on Graphics (TOG)
Color lines: image specific color representation
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Describing Reflectances for Color Segmentation Robust to Shadows, Highlights, and Textures
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image inpainting based on probabilistic structure estimation
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
Hi-index | 0.00 |
We propose a color-aware regularization for use with gradient domain image manipulation to avoid color shift artifacts. Our work is motivated by the observation that colors of objects in natural images typically follow distinct distributions in the color space. Conventional regularization methods ignore these distributions which can lead to undesirable colors appearing in the final output. Our approach uses an anisotropic Mahalanobis distance to control output colors to better fit original distributions. Our color-aware regularization is simple, easy to implement, and does not introduce significant computational overhead. To demonstrate the effectiveness of our method, we show the results with and without our color-aware regularization on three gradient domain tasks: gradient transfer, gradient boosting, and saliency sharpening.