Deep Learning Anti-Aliasing

<p>Deep Learning Anti-Aliasing (DLAA) is a form of <a href="/facts/Spatial_anti-aliasing/od0SgvLy">spatial anti-aliasing</a> developed by <a href="/facts/Nvidia/8QfCgqbu">Nvidia</a>. DLAA depends on and requires <a href="/facts/Tensor_Cores/qcowmpae">Tensor Cores</a> available in Nvidia RTX cards.
</p><p>DLAA is similar to <a href="/facts/Deep_Learning_Super_Sampling/qcowmpae">Deep Learning Super Sampling</a> (DLSS) in its <a href="/facts/Anti-aliasing/m3Ew0TQ6">anti-aliasing</a> method, with one important differentiation being that the goal of DLSS is to increase performance at the cost of image quality, whereas the main priority of DLAA is improving image quality at the cost of performance (irrelevant of resolution upscaling or downscaling). DLAA is similar to <a href="/facts/Temporal_anti-aliasing/ktQNm1FH">temporal anti-aliasing</a> (TAA) in that they are both spatial anti-aliasing solutions relying on past frame data. Compared to TAA, DLAA is substantially better when it comes to shimmering, flickering, and handling small meshes like wires.
</p>

Deep Learning Anti-Aliasing open-in-new

Deep Learning Anti-Aliasing