Morphological antialiasing

Reshetov, Alexander

doi:10.1145/1572769.1572787

Cited by 64 publications

(37 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although recent related techniques like CSAA [You06] and EQAA [AMD11] reduce bandwidth and storage costs by decoupling coverage from color, depth and stencil, these methods still inherit MSAA drawbacks. Other solutions, such as morphological antialiasing (MLAA) [Res09], try to estimate the pixel coverage of the original geometry based on the color discontinuities found in the final image. Reshetov's original work provides great results, but the proposed CPU implementation is not fast enough to be used in real-time.…”

Section: Related Workmentioning

confidence: 99%

“…Morphological antialiasing (MLAA) [Res09], tries to estimate the pixel coverage of the original geometry. To accu- Figure 2: MLAA first finds edges by looking for color discontinuities (green lines), and classifies them according to a series of pre-defined pattern shapes, which are then virtually re-vectorized (blue line), allowing to calculate the coverage areas a for the involved pixels.…”

Section: Morphological Antialiasingmentioning

confidence: 99%

“…Then, since the background cannot be known after rasterization, MLAA blends with a neighbor, assuming that its value is similar to the original background. Figure 2 describes this process; we refer the reader to the original publication for a more detailed explanation [Res09]. Its key feature is the use of novel texture structures for great performance improvements.…”

Section: Morphological Antialiasingmentioning

confidence: 99%

See 2 more Smart Citations

SMAA: Enhanced Subpixel Morphological Antialiasing

Jiménez

Echevarria

Sousa³

et al. 2012

Computer Graphics Forum

View full text Add to dashboard Cite

Figure 1: Example of SMAA 4x integrated in the Crysis 2 game. The insets show the differences between MLAA [JME * 11], our novel SMAA T2x and 4x algorithms and MSAA 8x as reference. For 1080p frames, the average cost of SMAA T2x is 1.3 ms and 2.6 ms for SMAA 4x, measured on a NVIDIA GeForce GTX 470. AbstractWe present a new image-based, post-processing antialiasing technique, which offers practical solutions to the common, open problems of existing filter-based real-time antialiasing algorithms. Some of the new features include local contrast analysis for more reliable edge detection, and a simple and effective way to handle sharp geometric features and diagonal lines. This, along with our accelerated and accurate pattern classification allows for a better reconstruction of silhouettes. Our method shows for the first time how to combine morphological antialiasing (MLAA) with additional multi/supersampling strategies (MSAA, SSAA) for accurate subpixel features, and how to couple it with temporal reprojection; always preserving the sharpness of the image. All these solutions combine synergies making for a very robust technique, yielding results of better overall quality than previous approaches while more closely converging to MSAA/SSAA references but maintaining extremely fast execution times. Additionally, we propose different presets to better fit the available resources or particular needs of each scenario.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Morphological Antialiasingmentioning

confidence: 99%

Section: Morphological Antialiasingmentioning

confidence: 99%

See 1 more Smart Citation

SMAA: Enhanced Subpixel Morphological Antialiasing

Jiménez

Echevarria

Sousa³

et al. 2012

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…MLAA (Reshetov, 2009) is an image-based algorithm providing full-image antialiasing independently of the rendering pipeline. Therefore it can be used in rasterization as well as in raytracing.…”

Section: Image-based Antialiasingmentioning

confidence: 99%

“…Due to the popularity of deferred rendering approaches in recent real-time rendering engines, a number of filter-based antialiasing techniques appeared. Morphological Antialiasing (Reshetov, 2009) (MLAA) is a relatively recent technique which enables full image antialiasing as a post-process. Figure 1 compares two images corrected by respectively MSAA and MLAA with similar results.…”

Section: Introductionmentioning

confidence: 99%

Morphological Antialiasing and Topological Reconstruction

Herubel

Biri

Deverly

2011

Proceedings of the International Conference on Computer Graphics Theory and Applications

View full text Add to dashboard Cite

Abstract:Morphological antialiasing is a post-processing approach which does note require additional samples computation. This algorithm acts as a non-linear filter, ill-suited to massively parallel hardware architectures. We redesigned the initial method using multiple passes with, in particular, a new approach to line length computation. We also introduce in the method the notion of topological reconstruction to correct the weaknesses of postprocessing antialiasing techniques. Our method runs as a pure post-process filter providing full-image antialiasing at high framerates, competing with traditional MSAA.

show abstract

Neural foveated super‐resolution for real‐time VR rendering

Ye,

Meng,

Guo

et al. 2024

Computer Animation & Virtual

View full text Add to dashboard Cite

As virtual reality display technologies advance, resolutions and refresh rates continue to approach human perceptual limits, presenting a challenge for real‐time rendering algorithms. Neural super‐resolution is promising in reducing the computation cost and boosting the visual experience by scaling up low‐resolution renderings. However, the added workload of running neural networks cannot be neglected. In this article, we try to alleviate the burden by exploiting the foveated nature of the human visual system, in a way that we upscale the coarse input in a heterogeneous manner instead of uniform super‐resolution according to the visual acuity decreasing rapidly from the focal point to the periphery. With the help of dynamic and geometric information (i.e., pixel‐wise motion vectors, depth, and camera transformation) available inherently in the real‐time rendering content, we propose a neural accumulator to effectively aggregate the amortizedly rendered low‐resolution visual information from frame to frame recurrently. By leveraging a partition‐assemble scheme, we use a neural super‐resolution module to upsample the low‐resolution image tiles to different qualities according to their perceptual importance and reconstruct the final output adaptively. Perceptually high‐fidelity foveated high‐resolution frames are generated in real‐time, surpassing the quality of other foveated super‐resolution methods.

show abstract

Morphological antialiasing

Cited by 64 publications

References 16 publications

SMAA: Enhanced Subpixel Morphological Antialiasing

SMAA: Enhanced Subpixel Morphological Antialiasing

Morphological Antialiasing and Topological Reconstruction

Neural foveated super‐resolution for real‐time VR rendering

Contact Info

Product

Resources

About