Deep Learning Super Sampling

Nvidia advertised DLSS as a key feature of GeForce RTX 20 series GPUs when they launched in September 2018. At that time, the results were limited to a few video games, namely Battlefield V, or Metro Exodus, because the algorithm had to be trained specifically on each game on which it was applied and the results were usually not as good as simple resolution upscaling. In 2019, Control shipped with ray tracing and an image processing algorithm that approximated DLSS, which did not use the Tensor Cores. In April 2020, Nvidia advertised and shipped an improved version of DLSS named DLSS 2 with driver version 445.75. DLSS 2.0 was available for a few existing games including Control and Wolfenstein: Youngblood, and would later be added to many newly released games and game engines such as Unreal Engine and Unity. This time Nvidia said that it used the Tensor Cores again, and that the AI did not need to be trained specifically on each game. Despite sharing the DLSS branding, the two iterations of DLSS differ significantly and are not backwards-compatible. In January 2025, Nvidia stated that there are over 540 games and apps supporting DLSS, and that over 80% of Nvidia RTX users activate DLSS. In March 2025, there were more than 100 games that support DLSS 4, according to Nvidia. By May 2025, over 125 games supported DLSS 4. The first video game console to use DLSS, the Nintendo Switch 2, was released on June 5, 2025. Nvidia announced DLSS 4.5 at CES 2026. In January 2026, Nvidia stated that over 250 games and applications support Multi Frame Generation. On March 16, 2026, at GTC 2026, Nvidia CEO Jensen Huang presented DLSS 5, a real-time AI model based on neural rendering that realistically enhances lighting and material surfaces at up to 4K resolution while retaining the developer's intended art style. In a blog post on its website, Nvidia has announced that DLSS 5 will be available in such games as ''Assassin's Creed Shadows, Delta Force, Hogwarts Legacy, Naraka: Bladepoint, Phantom Blade Zero, Resident Evil Requiem, Starfield, The Elder Scrolls IV: Oblivion Remastered'', and more. Release timeline == Technology ==

DLSS 1 The first iteration of DLSS is a predominantly spatial image upscaler with two stages, both relying on convolutional auto-encoder neural networks. The first step is an image enhancement network which uses the current frame and motion vectors to perform edge enhancement, and spatial anti-aliasing. The second stage is an image upscaling step which uses the single raw, low-resolution frame to upscale the image to the desired output resolution. Using just a single frame for upscaling means the neural network itself must generate a large amount of new information to produce the high-resolution output, which can result in slight hallucinations such as leaves that differ in style to the source content. This first iteration received a mixed response, with many criticizing the often soft appearance and artifacts along with glitches in certain situations; TAA(U) is used in many modern video games and game engines; 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. so this could suggest some minor training optimizations may be performed as games are released, although Nvidia does not provide changelogs for these minor revisions to confirm this. The main advancements compared to DLSS 1 include: Significantly improved detail retention, a generalized neural network that does not need to be re-trained per-game, and ~2x less overhead (~1–2 ms vs ~2–4 ms). DLSS 3.5 DLSS 3.5 adds Ray Reconstruction, replacing multiple denoising algorithms with a single AI model trained on five times more data than DLSS 3. Ray Reconstruction is available on all RTX GPUs and first targeted games with path tracing (aka "full ray tracing"), including Cyberpunk 2077's Phantom Liberty DLC, Portal with RTX, and Alan Wake 2. DLSS 4 allows a greater number of frames to be generated and interpolated based on a single traditionally rendered frame. This form of frame generation called Multi Frame Generation is exclusive to the GeForce RTX 50 series while the GeForce RTX 40 series is limited to one interpolated frame per traditionally rendered frame. Nvidia claims that DLSS 4x Frame Generation model uses 30% less video memory with the example of Warhammer 40,000: Darktide using 400MB less memory at 4K resolution with Frame Generation enabled. Nvidia claims that 75 games will integrate DLSS 4 Multi Frame Generation at launch, including Alan Wake 2, Cyberpunk 2077, Indiana Jones and the Great Circle, and Star Wars Outlaws. DLSS 4.5 DLSS 4.5 introduces Dynamic Multi Frame Generation, which can dynamically generate up to 6x the amount of frames for GeForce RTX 50-series GPUs, and upgrades the transformer model used for upscaling to a second-generation model for better temporal stability, ghosting and anti-aliasing. On RTX 30 series and older, DLSS 4.5 is around 5 times more computationally demanding because "Nvidia is leveraging FP8 precision in RTX 40 and RTX 50 series cards for DLSS 4.5 to lessen the performance impact on newer cards." DLSS 5 DLSS 5, announced at GTC 2026, uses a neural rendering-based AI model to enhance lighting and material surfaces in real time at up to 4K resolution. Nvidia described the technology as retaining the developer's intended art style. It operates on similar principles to TAA. Like TAA, it uses information from past frames to produce the current frame. Unlike TAA, DLSS does not sample every pixel in every frame. Instead, it samples different pixels in different frames and uses pixels sampled in past frames to fill in the unsampled pixels in the current frame. DLSS uses machine learning to combine samples in the current frame and past frames, and is made possible by the available tensor cores. Nvidia also offers Deep Learning Anti-Aliasing (DLAA), which provides the same AI-driven anti-aliasing DLSS uses, but without any upscaling or downscaling. == Hardware ==

With the exception of the shader-core version implemented in Control, DLSS is only available on GeForce RTX 20, GeForce RTX 30, GeForce RTX 40, GeForce RTX 50, and Quadro RTX series of video cards, using dedicated AI accelerators called Tensor Cores. They are used for doing fused multiply-add (FMA) operations that are used extensively in neural network calculations for applying a large series of multiplications on weights, followed by the addition of a bias. Tensor cores can operate on FP16, INT8, INT4, and INT1 data types. Each core can do 1024 bits of FMA operations per clock, so 1024 INT1, 256 INT4, 128 INT8, and 64 FP16 operations per clock per tensor core, and most Turing GPUs have a few hundred tensor cores. The Tensor Cores use CUDA Warp-Level Primitives on 32 parallel threads to take advantage of their parallel architecture. A Warp is a set of 32 threads which are configured to execute the same instruction. Since Windows 10 version 1903, Microsoft provided DirectML as one part of DirectX to support Tensor Cores. == Quality presets ==

When using DLSS, depending on the game, users have access to various quality presets in addition to the option to set the internally rendered, upscaled resolution manually: == Software ==

Manually upgrading DLSS Users can manually replace the DLLs in games to support a newer version of DLSS. DLSS Swapper, an open source utility, can automatically do this for all installed games. Replacing DLL files can not add DLSS support or features to games that do not already implement them, though some mods can add frame generation support. It is also possible to override the DLSS version without touching game files via the Nvidia App. Nvidia App DLSS model presets While the Nvidia App does not specify the DLSS version used in each preset available, the following table summarizes this information. == Reception ==

Particularly in early versions of DLSS, users reported blurry frames. Andrew Edelsten, an employee at Nvidia, therefore commented on the problem in a blog post in 2019 and promised that they were working on improving the technology and clarified that the DLSS AI algorithm was mainly trained with 4K image material. That the use of DLSS leads to particularly blurred images at lower resolutions, such as Full HD, is due to the fact that the algorithm has far less image information available to calculate an appropriate image compared to higher resolutions like 4K. The use of DLSS Frame Generation leads to increased input latency, as well as visual artifacts. It has also been criticized that by implementing DLSS in their games, game developers no longer have an incentive to optimize them so that they also run smoothly in native resolution on modern PC hardware. For example, for the game Alan Wake 2 in 4K at the highest graphics settings with ray tracing enabled, the use of DLSS in Performance mode is recommended even with graphics cards such as the Nvidia GeForce RTX 4080 in order to achieve 60 fps. The transformer-based AI upscaling model introduced with DLSS 4 received moderate praise for its improved image quality with regard to increased stability, reduced ghosting, better anti-aliasing, and higher level of detail, as well as its backward compatibility and higher training scalability regarding future improvements. ComputerBase found that "DLSS 4.5 effectively addresses the very issues that DLSS 4 still had problems with, and many of these issues have been partially or completely resolved." While "[t]he higher performance requirements are [...] not ideal", they "can generally be handled by RTX 4000 and RTX 5000 cards." DLSS 5 controversy Upon its announcement at GTC 2026, DLSS 5 received significant backlash from both gamers and game developers on social media. Critics argued that the technology's neural rendering-based approach altered games' art direction in ways not intended by their developers, with some comparing its output to AI slop. The technology's handling of human faces drew particular criticism. The Verge highlighted an example from EA Sports FC 26 in which Liverpool captain Virgil van Dijk's facial features were noticeably distorted by the technology, and compared the overall effect to motion smoothing on televisions. IGN characterized DLSS 5 as undermining the artistic craft of video game design, and Engadget argued that the negative reaction from gamers was justified. == See also ==