Bilateral Filtering for Gray and Color Images
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Colorization using optimization
ACM SIGGRAPH 2004 Papers
Interactive local adjustment of tonal values
ACM SIGGRAPH 2006 Papers
AppWand: editing measured materials using appearance-driven optimization
ACM SIGGRAPH 2007 papers
Real-time edge-aware image processing with the bilateral grid
ACM SIGGRAPH 2007 papers
AppProp: all-pairs appearance-space edit propagation
ACM SIGGRAPH 2008 papers
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach
International Journal of Computer Vision
Edge-avoiding wavelets and their applications
ACM SIGGRAPH 2009 papers
Efficient affinity-based edit propagation using K-D tree
ACM SIGGRAPH Asia 2009 papers
Diffusion maps for edge-aware image editing
ACM SIGGRAPH Asia 2010 papers
Data-driven image color theme enhancement
ACM SIGGRAPH Asia 2010 papers
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
ACM Transactions on Graphics (TOG)
Semantic colorization with internet images
Proceedings of the 2011 SIGGRAPH Asia Conference
Antialiasing recovery for edit propagation
Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry
EGSR'08 Proceedings of the Nineteenth Eurographics conference on Rendering
A sparse control model for image and video editing
ACM Transactions on Graphics (TOG)
WYSIWYG computational photography via viewfinder editing
ACM Transactions on Graphics (TOG)
| Hi-index | 0.00 |
We propose a novel edit propagation algorithm for interactive image and video manipulations. Our approach uses the locally linear embedding (LLE) to represent each pixel as a linear combination of its neighbors in a feature space. While previous methods require similar pixels to have similar results, we seek to maintain the manifold structure formed by all pixels in the feature space. Specifically, we require each pixel to be the same linear combination of its neighbors in the result. Compared with previous methods, our proposed algorithm is more robust to color blending in the input data. Furthermore, since every pixel is only related to a few nearest neighbors, our algorithm easily achieves good runtime efficiency. We demonstrate our manifold preserving edit propagation on various applications.