Deep learning anti-aliasing

rdf:langString Deep learning anti-aliasing

rdf:langString Deep learning anti-aliasing (DLAA) is a form of spatial anti-aliasing created by Nvidia. DLAA depends on and requires Tensor Cores available in Nvidia RTX cards. DLAA is similar to deep learning super sampling (DLSS) in its anti-aliasing method, with one important differentiation being that DLSS's goal is to increase performance at the cost of image quality, where the main priority of DLAA is improving image quality at the cost of performance, irrelevant of resolution upscaling or downscaling. DLAA is similar to temporal anti-aliasing (TAA) in that they're 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. DLAA collects game rendering data such as raw low-resolution input, motion vectors, depth buffers, and exposure / brightness information. This Information is then used by DLAA to improve upon its anti-aliasing, with the aim of reducing temporal instability.