Paint by numbers: abstract image representations
SIGGRAPH '90 Proceedings of the 17th annual conference on Computer graphics and interactive techniques
Stylization and abstraction of photographs
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Bilateral Filtering for Gray and Color Images
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Interactive watercolor rendering with temporal coherence and abstraction
Proceedings of the 4th international symposium on Non-photorealistic animation and rendering
ACM SIGGRAPH 2006 Papers
Structure-preserving manipulation of photographs
Proceedings of the 5th international symposium on Non-photorealistic animation and rendering
Video watercolorization using bidirectional texture advection
ACM SIGGRAPH 2007 papers
IEEE Transactions on Visualization and Computer Graphics
GradientShop: A gradient-domain optimization framework for image and video filtering
ACM Transactions on Graphics (TOG)
Smoothed local histogram filters
ACM SIGGRAPH 2010 papers
NPAR '10 Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering
Geodesic image and video editing
ACM Transactions on Graphics (TOG)
Domain transform for edge-aware image and video processing
ACM SIGGRAPH 2011 papers
Image and video abstraction by multi-scale anisotropic Kuwahara filtering
Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Non-Photorealistic Animation and Rendering
Image simplification and vectorization
Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Non-Photorealistic Animation and Rendering
Artistic Edge and Corner Enhancing Smoothing
IEEE Transactions on Image Processing
Texture-preserving abstraction
NPAR '12 Proceedings of the Symposium on Non-Photorealistic Animation and Rendering
| Hi-index | 0.00 |
Image abstraction traditionally eliminates texture, flattening gradients and removing small-scale details. However, abstracting while preserving irregular silhouettes and medium-scale details can produce a richer abstracted image. We propose a variant of geodesic image filtering which preserves the locally strongest edges, leading to preservation of both strong edges and weak edges depending on the surrounding context. Our contribution is to introduce cumulative range geodesic filtering, where the distance in the image plane is lengthened proportional to the color distance from the starting point. We apply the new filtering scheme to abstraction applications in images and video, and demonstrate that it has powerful structure-preserving capabilities, especially regarding preservation and indication of irregular details. The basic technique, where every pixel is equally abstracted, is further extended with explorations of variable mask size based on spatial location, salience, intensity, and location combined with intensity.