Deep learning anti-aliasing (DLAA) is a form of

spatial anti-aliasing In digital signal processing, spatial anti-aliasing is a technique for minimizing the distortion artifacts ( aliasing) when representing a high-resolution image at a lower resolution. Anti-aliasing is used in digital photography, computer graphi ...

created by

Nvidia Nvidia CorporationOfficially written as NVIDIA and stylized in its logo as VIDIA with the lowercase "n" the same height as the uppercase "VIDIA"; formerly stylized as VIDIA with a large italicized lowercase "n" on products from the mid 1990s to ...

. DLAA depends on and requires

Tensor Cores Deep learning super sampling (DLSS) is a family of real-time deep learning image enhancement and upscaling technologies developed by Nvidia that are exclusive to its RTX line of graphics cards, and available in a number of video games. The goal ...

available in Nvidia RTX cards. DLAA is similar to

deep learning super sampling Deep learning super sampling (DLSS) is a family of real-time deep learning image enhancement and upscaling technologies developed by Nvidia that are exclusive to its RTX line of graphics cards, and available in a number of video games. The goal o ...

(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 Temporal anti-aliasing (TAA) is a spatial anti-aliasing technique for computer-generated video that combines information from past frames and the current frame to remove jaggies in the current frame. In TAA, each pixel is sampled once per frame but ...

(TAA) in that they're both

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.

Differences between TAA and DLAA

TAA is used in many modern video games and game engines, however all previous implementations have used some form of manually written

heuristic A heuristic (; ), or heuristic technique, is any approach to problem solving or self-discovery that employs a practical method that is not guaranteed to be optimal, perfect, or rational, but is nevertheless sufficient for reaching an immediate ...

s to prevent temporal artifacts such as ghosting and flickering. One example of this is neighborhood clamping which forcefully prevents samples collected in previous frames from deviating too much compared to nearby pixels in newer frames. This helps to identify and fix many temporal artifacts, but deliberately removing fine details in this way is analogous to applying a blur filter, and thus the final image can appear blurry when using this method. DLAA uses a convolutional auto-encoder neural network trained to identify and fix temporal artifacts, instead of manually programmed heuristics as mentioned above. Because of this, DLAA can generally resolve detail better than other TAA and TAAU implementations, while also removing most temporal artifacts.

Differences between DLSS and DLAA

DLSS handles upscaling with a focus on performance, DLAA handles anti-aliasing with a focus on visual quality. DLAA runs at the given screen resolution with no upscaling or downscaling functionality. DLSS and DLAA share the same AI-driven anti-aliasing method. Both are made by

and require Tensor Cores.

References

{{Compu-graphics-stub Anti-aliasing algorithms

Differences between TAA and DLAA

Differences between DLSS and DLAA

See also

References