SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques
Illumination for computer generated pictures
Communications of the ACM
Use of the Hough transformation to detect lines and curves in pictures
Communications of the ACM
Duality and Geometry in SVM Classifiers
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Human vision, anti-aliasing, and the cheap 4000 line display
SIGGRAPH '80 Proceedings of the 7th annual conference on Computer graphics and interactive techniques
Combining edges and points for interactive high-quality rendering
ACM SIGGRAPH 2003 Papers
Image upsampling via imposed edge statistics
ACM SIGGRAPH 2007 papers
Accelerating real-time shading with reverse reprojection caching
Proceedings of the 22nd ACM SIGGRAPH/EUROGRAPHICS symposium on Graphics hardware
Proceedings of the Conference on High Performance Graphics 2009
A directionally adaptive edge anti-aliasing filter
Proceedings of the Conference on High Performance Graphics 2009
ACM SIGGRAPH Asia 2009 papers
Spatio-temporal upsampling on the GPU
Proceedings of the 2010 ACM SIGGRAPH symposium on Interactive 3D Graphics and Games
Practical morphological antialiasing on the GPU
ACM SIGGRAPH 2010 Talks
Subpixel reconstruction antialiasing for deferred shading
I3D '11 Symposium on Interactive 3D Graphics and Games
Filtering approaches for real-time anti-aliasing
ACM SIGGRAPH 2011 Courses
I3D '12 Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games
SMAA: Enhanced Subpixel Morphological Antialiasing
Computer Graphics Forum
Geometry-aware framebuffer level of detail
EGSR'08 Proceedings of the Nineteenth Eurographics conference on Rendering
Hi-index | 0.00 |
Post-processing antialiasing methods are well suited for deferred shading because they decouple antialiasing from the rest of graphics pipeline. In morphological methods, the final image is filtered with a data-dependent filter. The filter coefficients are computed by analyzing the non-local neighborhood of each pixel. Though very simple and efficient, such methods have intrinsic quality limitations due to spatial undersampling and temporal aliasing. We explore an alternative formulation in which filter coefficients are computed locally for each pixel by supersampling geometry, while shading is still done only once per pixel. During pre-processing, each geometric subsample is converted to a single bit indicating whether the subsample is different from the central one. The ensuing binary mask is then used in the post-processing step to retrieve filter coefficients, which were precomputed for all possible masks. For a typical 8 subsamples, it results in a sub-millisecond performance, while improving the image quality by about 10 dB. To compare subsamples, we use a novel symmetric angular measure, which has a simple geometric interpretation. We propose to use this measure in a variety of applications that assess the difference between geometric samples (rendering, mesh simplification, geometry encoding, adaptive tessellation).