Deep Learning Anti-Aliasing

Last updated

Deep Learning Anti-Aliasing (DLAA) is a form of spatial anti-aliasing developed by Nvidia. [1] DLAA depends on and requires Tensor Cores available in Nvidia RTX cards. [1]

Contents

DLAA is similar to Deep Learning Super Sampling (DLSS) in its anti-aliasing method, [2] with one important differentiation being that the goal of DLSS is to increase performance at the cost of image quality, [3] whereas the main priority of DLAA is improving image quality at the cost of performance (irrelevant of resolution upscaling or downscaling). [4] DLAA is similar to temporal anti-aliasing (TAA) in that they are both spatial anti-aliasing solutions relying on past frame data. [3] [5] Compared to TAA, DLAA is substantially better when it comes to shimmering, flickering, and handling small meshes like wires. [6]

Technical overview

DLAA collects game rendering data including raw low-resolution input, motion vectors, depth buffers, and exposure information. This information feeds into a convolutional neural network that processes the image to reduce aliasing while preserving fine detail. [3]

The neural network architecture employs an auto-encoder design trained on high-quality reference images. The training dataset includes diverse scenarios focusing on challenging cases like sub-pixel details, high-contrast edges, and transparent surfaces. The network then processes frames in real-time. [3]

Unlike traditional anti-aliasing solutions that rely on manually written heuristics, such as TAA, DLAA uses its neural network to preserve fine details while eliminating unwanted visual artifacts. [3]

History

The first game that added support for DLAA was The Elder Scrolls Online , which implemented the feature in 2021. [7] [8] [9] By June 2022, DLAA was only available in six games. [10] This number rose to 17 by February 2023. [11] [12] In June 2023, TechPowerUp reported that "DLAA is seeing sluggish adoption among game developers", and that Nvidia was working on adding DLAA to the quality presets of DLSS to boost adoption. [13] As of December 2023, DLAA is supported in 41 games. [9]

Differences between TAA and DLAA

TAA is used in many modern video games and game engines; [14] however, all previous implementations have used some form of manually written heuristics 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. [15]

DLAA uses an auto-encoder convolutional neural network [16] 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

While 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 provided by DLAA. [17]

DLSS and DLAA share the same AI-driven anti-aliasing method. [18] As such, DLAA functions like DLSS without the upscaling part. Both are made by Nvidia and require Tensor Cores. However, DLSS and DLAA cannot be enabled at the same time, only one can be selected depending on whether performance or image quality is prioritized.

Reception

TechPowerUp found that "[c]ompared to TAA and DLSS, DLAA is clearly producing the best image quality, especially at lower resolutions", arguing that, while "DLSS was already doing a better job than TAA at reconstructing small objects", "DLAA does an even better job". [17]

In a Cyberpunk 2077 performance test, IGN found that "DLAA provided somewhat similar results [FPS wise] to the normal raster mode in most cases but got significant performance boost with the help of frame generation", a feature not available when using native resolution. [19]

Rock Paper Shotgun found that, while DLAA is "not a completely perfect form of anti-aliasing, as the occasional jaggies are present", it "looks a lot sharper overall [than TAA], and especially in motion." [10]

References

  1. 1 2 Kostovic, Aleksandar (2021-09-20). "Nvidia Readies Deep Learning Anti-Aliasing Debut with The Elder Scrolls Online Update". Tom's Hardware. Retrieved 2022-02-20.
  2. ↑ Hruska, Joel (2021-09-21). "Nvidia's DLAA Could Be a Huge Step Forward for Anti-Aliasing". ExtremeTech.
  3. 1 2 3 4 5 Liu, Edward (2020-03-23). "DLSS 2.0 – Image Reconstruction for Real-Time Rendering With Deep Learning" (PDF). Behind the Pixels.
  4. ↑ "Nvidia's DLAA makes PC games look better with little performance hit". PCWorld. Retrieved 2024-04-20.
  5. ↑ Yang, Lei; Liu, Shiqiu; Salvi, Marco. "A Survey of Temporal Antialiasing Techniques" (PDF). Computer Graphics Forum. 39 (2): 607–621. doi:10.1111/cgf.14018 – via Behind the Pixels.
  6. ↑ De Meo, Francesco (2021-09-23). "The Elder Scrolls Online DLAA vs DLSS vs TAA Comparison Video Highlights DLAA Superior Image Quality". Wccftech. Retrieved 2022-02-20.
  7. ↑ Dastoor, Vaspaan (2021-09-20). "The Elder Scrolls Online Will Be The First Game To Use Nvidia DLAA". TheGamer. Retrieved 2025-03-04.
  8. ↑ Hruska, Joel (2021-09-21). "Nvidia's DLAA Could Be a Huge Step Forward for Anti-Aliasing". ExtremeTech. Retrieved 2025-03-04.
  9. 1 2 Walton, Jarred (2023-12-04). "Nvidia reaches an RTX milestone, with over 500 games and applications that use DLSS, ray tracing, and AI features". Tom's Hardware. Retrieved 2025-03-04.
  10. 1 2 Editor, James Archer Hardware; Archer, James (2022-06-27). "Nvidia DLAA: How it works, supported games and performance vs DLSS". Rock, Paper, Shotgun. Retrieved 2025-03-04.{{cite news}}: |last= has generic name (help)
  11. ↑ Bashir, Samir (2023-02-14). "Game optimization software can enable DLAA support in DLSS-compatible games". igor´sLAB. Retrieved 2025-03-04.
  12. ↑ "Game tweaking tool can enable DLAA support in DLSS-compatible games". VideoCardz.com. Retrieved 2025-03-04.
  13. ↑ "NVIDIA Finds a Clever Way to Boost DLAA Adoption—To Turn it into a DLSS Preset". TechPowerUp. 2023-06-08. Retrieved 2025-03-06.
  14. ↑ Karis, Brian. "High Quality Temporal Supersamplin" (PDF).
  15. ↑ "GTC 2020: DLSS 2.0 - Image Reconstruction for Real-time Rendering with Deep Learning". NVIDIA Developer. 2020-06-09. Retrieved 2022-06-26.
  16. ↑ "NVIDIA DLSS 2.0: A Big Leap In AI Rendering". www.nvidia.com. Retrieved 2022-06-26.
  17. 1 2 maxus24 (2021-09-22). "NVIDIA DLAA Anti-Aliasing Review - DLSS at Native Resolution". TechPowerUp. Archived from the original on 2021-09-23. Retrieved 2025-02-22.
  18. ↑ Archer, James (2022-06-27). "Nvidia DLAA: How it works, supported games and performance vs DLSS". Rock, Paper, Shotgun. Retrieved 2025-02-22.
  19. ↑ Hooda, Rehan; Mathur, Moulik (2023-09-25). "Cyberpunk 2077: Phantom Liberty Performance Review". IGN India. Retrieved 2025-03-05.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.