Multi Frame Generation
   HOME

TheInfoList



OR:

Deep Learning Super Sampling (DLSS) is a suite of
real-time Real-time, realtime, or real time may refer to: Computing * Real-time computing, hardware and software systems subject to a specified time constraint * Real-time clock, a computer clock that keeps track of the current time * Real-time Control Syst ...
deep learning Deep learning is a subset of machine learning that focuses on utilizing multilayered neural networks to perform tasks such as classification, regression, and representation learning. The field takes inspiration from biological neuroscience a ...
image enhancement and upscaling technologies developed by
Nvidia Nvidia Corporation ( ) is an American multinational corporation and technology company headquartered in Santa Clara, California, and incorporated in Delaware. Founded in 1993 by Jensen Huang (president and CEO), Chris Malachowsky, and Curti ...
that are available in a number of
video game A video game or computer game is an electronic game that involves interaction with a user interface or input device (such as a joystick, game controller, controller, computer keyboard, keyboard, or motion sensing device) to generate visual fe ...
s. The goal of these technologies is to allow the majority of the
graphics pipeline The computer graphics pipeline, also known as the rendering pipeline, or graphics pipeline, is a framework within computer graphics that outlines the necessary procedures for transforming a three-dimensional (3D) scene into a two-dimensional (2 ...
to run at a lower resolution for increased performance, and then infer a higher resolution image from this that approximates the same level of detail as if the image had been rendered at this higher resolution. This allows for higher graphical settings and/or
frame rates Frame rate, most commonly expressed in frame/s, or FPS, is typically the frequency (rate) at which consecutive images (frames) are captured or displayed. This definition applies to film and video cameras, computer animation, and motion capture s ...
for a given output resolution, depending on user preference. All generations of DLSS are available on all RTX-branded cards from Nvidia in supported titles. However, the Frame Generation feature is only supported on 40 series GPUs or newer and Multi Frame Generation is only available on
50 series 50 series may refer to: Electronics * HP 49/50 series, a type of graphing calculator made by Hewlett-Packard * Nvidia GeForce RTX 50 series, a series of graphic card. Trains * 1–50 series (CTA), a retired subway car type for the Chicago ...
GPUs.


History

Nvidia advertised DLSS as a key feature of the
GeForce 20 series The GeForce RTX 20 series is a family of graphics processing units developed by Nvidia. Serving as the successor to the GeForce 10 series, the line started shipping on September 20, 2018, and after several editions, on July 2, 2019, the GeForc ...
cards when they launched in September 2018. At that time, the results were limited to a few video games, namely ''
Battlefield V ''Battlefield V'' is a 2018 first-person shooter game developed by DICE and published by Electronic Arts. The game is the successor to 2016's '' Battlefield 1'' and the eleventh main installment in the ''Battlefield'' series. It is based on Wor ...
'', 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, the video game '' Control'' shipped with
real-time ray tracing In 3D computer graphics, ray tracing is a technique for modeling Light transport theory, light transport for use in a wide variety of Rendering (computer graphics), rendering algorithms for generating digital image, digital images. On a spectr ...
and an improved version of DLSS, which did not use the Tensor Cores. In April 2020, Nvidia advertised and shipped an improved version of DLSS named DLSS 2.0 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 engine A game engine is a software framework primarily designed for the development of video games which generally includes relevant libraries and support programs such as a level editor. The "engine" terminology is akin to the term " software engine" u ...
s such as
Unreal Engine Unreal Engine (UE) is a 3D computer graphics game engine developed by Epic Games, first showcased in the 1998 first-person shooter video game '' Unreal''. Initially developed for PC first-person shooters, it has since been used in a variety of ...
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.Edward Liu, NVIDI
"DLSS 2.0 - Image Reconstruction for Real-time Rendering with Deep Learning"
/ref> In January 2025, Nvidia stated that there are over 540 games and apps supporting DLSS, and that over 80% of
Nvidia RTX Nvidia RTX (also known as Nvidia GeForce RTX under the GeForce brand) is a professional visual computing platform created by Nvidia, used in mainstream PCs for gaming as well as being used in workstations for designing complex large-scale model ...
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 A video game console is an electronic device that Input/output, outputs a video signal or image to display a video game that can typically be played with a game controller. These may be home video game console, home consoles, which are generally ...
to use DLSS, the
Nintendo Switch 2 The is a hybrid video game console developed by Nintendo, released in most regions on June5, 2025. Like the original Nintendo Switch, Switch, it can be used as a Handheld game console, handheld, as a Tablet computer, tablet, or connected via ...
, was released on June 5, 2025.


Release history


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:


Implementation


DLSS 1.0

The first iteration of DLSS is a predominantly spatial image upscaler with two stages, both relying on convolutional auto-encoder
neural network A neural network is a group of interconnected units called neurons that send signals to one another. Neurons can be either biological cells or signal pathways. While individual neurons are simple, many of them together in a network can perfor ...
s. The first step is an image enhancement network which uses the current frame and motion vectors to perform
edge enhancement Edge enhancement is an image processing filter that enhances the edge contrast of an image or video in an attempt to improve its acutance (apparent sharpness). The filter works by identifying sharp edge boundaries in the image, such as the edge ...
, and
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 graphics ...
. 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, this can result in slight
hallucination A hallucination is a perception in the absence of an external stimulus that has the compelling sense of reality. They are distinguishable from several related phenomena, such as dreaming ( REM sleep), which does not involve wakefulness; pse ...
s such as leaves that differ in style to the source content. The neural networks are trained on a per-game basis by generating a "perfect frame" using traditional
supersampling Supersampling or supersampling anti-aliasing (SSAA) is a spatial anti-aliasing method, i.e. a method used to remove aliasing (jagged and pixelated edges, colloquially known as "jaggies") from images rendered in computer games or other computer p ...
to 64 samples per pixel, as well as the motion vectors for each frame. The data collected must be as comprehensive as possible, including as many levels, times of day, graphical settings, resolutions, etc. as possible. This data is also
augmented Augment or augmentation may refer to: Language *Augment (Indo-European), a syllable added to the beginning of the word in certain Indo-European languages * Augment (Bantu languages), a morpheme that is prefixed to the noun class prefix of nouns ...
using common augmentations such as rotations, colour changes, and random noise to help generalize the test data. Training is performed on Nvidia's Saturn V supercomputer. This first iteration received a mixed response, with many criticizing the often soft appearance and artifacts in certain situations; likely a side effect of the limited data from only using a single frame input to the neural networks which could not be trained to perform optimally in all scenarios and edge-cases. Nvidia also demonstrated the ability for the auto-encoder networks to learn the ability to recreate depth-of-field and
motion blur Motion blur is the apparent streaking of moving objects in a photograph or a sequence of frames, such as a film or animation. It results when the image being recorded changes during the recording of a single exposure, due to rapid movement or l ...
, although this functionality has never been included in a publicly released product.


DLSS 2.0

DLSS 2.0 is a
temporal anti-aliasing Temporal anti-aliasing (TAA), also known as TXAA (a proprietary technology) or TMAA/TSSAA (''Temporal Super-Sampling Anti-Aliasing''), is a spatial anti-aliasing technique for computer-generated video that combines information from past frames and ...
upsampling In digital signal processing, upsampling, expansion, and interpolation are terms associated with the process of sample rate conversion, resampling in a multi-rate digital signal processing system. ''Upsampling'' can be synonymous with ''expansion'' ...
(TAAU) implementation, using data from previous frames extensively through sub-pixel jittering to resolve fine detail and reduce aliasing. The data DLSS 2.0 collects includes: the raw low-resolution input,
motion vector In computer vision and image processing, motion estimation is the process of determining ''motion vectors'' that describe the transformation from one 2D image to another; usually from adjacent frames in a video sequence. It is an ill-posed prob ...
s, depth buffers, and exposure / brightness information. It can also be used as a simpler TAA implementation where the image is rendered at 100% resolution, rather than being upsampled by DLSS, Nvidia brands this as DLAA (Deep Learning Anti-Aliasing). TAA(U) is used in many modern video games and
game engine A game engine is a software framework primarily designed for the development of video games which generally includes relevant libraries and support programs such as a level editor. The "engine" terminology is akin to the term " software engine" u ...
s; however, all previous implementations have used some form of manually written
heuristic A heuristic or heuristic technique (''problem solving'', '' mental shortcut'', ''rule of thumb'') is any approach to problem solving that employs a pragmatic method that is not fully optimized, perfected, or rationalized, but is nevertheless ...
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. DLSS 2.0 uses a convolutional auto-encoder
neural network A neural network is a group of interconnected units called neurons that send signals to one another. Neurons can be either biological cells or signal pathways. While individual neurons are simple, many of them together in a network can perfor ...
trained to identify and fix temporal artifacts, instead of manually programmed heuristics as mentioned above. Because of this, DLSS 2.0 can generally resolve detail better than other TAA and TAAU implementations, while also removing most temporal artifacts. This is why DLSS 2.0 can sometimes produce a sharper image than rendering at higher, or even native resolutions using traditional TAA. However, no temporal solution is perfect, and artifacts (ghosting in particular) are still visible in some scenarios when using DLSS 2.0. Because temporal artifacts occur in most art styles and environments in broadly the same way, the neural network that powers DLSS 2.0 does not need to be retrained when being used in different games. Despite this, Nvidia does frequently ship new minor revisions of DLSS 2.0 with new titles, 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 1.0 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). It should also be noted that forms of TAAU such as DLSS 2.0 are not upscalers in the same sense as techniques such as ESRGAN or DLSS 1.0, which attempt to create new information from a low-resolution source; instead, TAAU works to recover data from previous frames, rather than creating new data. In practice, this means low resolution textures in games will still appear low-resolution when using current TAAU techniques. This is why Nvidia recommends game developers use higher resolution textures than they would normally for a given rendering resolution by applying a mip-map bias when DLSS 2.0 is enabled.


DLSS 3.0

Augments DLSS 2.0 by making use of
motion interpolation Motion interpolation, motion-compensated frame interpolation (MCFI), or frame generation is a form of video processing in which intermediate film, video or animation frames are synthesized between existing ones by means of interpolation, in an at ...
. The DLSS Frame Generation algorithm takes two rendered frames from the rendering pipeline and generates a new frame that smoothly transitions between them. So for every frame rendered, one additional frame is generated. DLSS 3.0 makes use of a new generation Optical Flow Accelerator (OFA) included in Ada Lovelace generation RTX GPUs. The new OFA is faster and more accurate than the OFA already available in previous Turing and Ampere RTX GPUs. This results in DLSS 3.0 being exclusive for the RTX 40 Series. At release, DLSS 3.0 does not work for VR displays.


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 Path tracing is a rendering algorithm in computer graphics that Simulation, simulates how light interacts with Physical object, objects, voxels, and Volumetric_path_tracing, participating media to generate realistic (''physically plausible'') R ...
(aka "full ray tracing"), including ''
Cyberpunk 2077 ''Cyberpunk 2077'' is a 2020 action role-playing game developed by CD Projekt Red and published by CD Projekt. Based on Mike Pondsmith's ''Cyberpunk (role-playing game), Cyberpunk'' tabletop game series, the plot is set in the fictional metrop ...
s ''
Phantom Liberty ''Cyberpunk 2077: Phantom Liberty'' () is a 2023 expansion pack for the 2020 video game ''Cyberpunk 2077'' developed by CD Projekt Red. The expansion introduces a new district to the game's open world, as well as a new quest line. In a dystopia ...
'' DLC, '' Portal with RTX'', and '' Alan Wake 2''.


DLSS 4.0

The fourth generation of Deep Learning Super Sampling (DLSS) was unveiled alongside the
GeForce RTX 50 series The GeForce RTX 50 series is a series of consumer graphics processing units (GPUs) developed by Nvidia as part of its GeForce line of graphics cards, succeeding the GeForce 40 series. Announced at CES 2025, it debuted with the release of the ...
. DLSS 4 upscaling uses a new vision
transformer In electrical engineering, a transformer is a passive component that transfers electrical energy from one electrical circuit to another circuit, or multiple Electrical network, circuits. A varying current in any coil of the transformer produces ...
-based model for enhanced image quality with reduced ghosting and greater image stability in motion compared to the previous
convolutional neural network A convolutional neural network (CNN) is a type of feedforward neural network that learns features via filter (or kernel) optimization. This type of deep learning network has been applied to process and make predictions from many different ty ...
(CNN) model. 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. According to Nvidia, this technique will increase performance by up to 800% while retaining low latency with Nvidia Reflex. 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 ''Cyberpunk 2077'' is a 2020 action role-playing game developed by CD Projekt Red and published by CD Projekt. Based on Mike Pondsmith's ''Cyberpunk (role-playing game), Cyberpunk'' tabletop game series, the plot is set in the fictional metrop ...
'', ''
Indiana Jones and the Great Circle ''Indiana Jones and the Great Circle'' is a 2024 action-adventure game developed by MachineGames and published by Bethesda Softworks. It is based on the ''Indiana Jones'' franchise and features an original narrative that draws from the film ser ...
'', and ''
Star Wars Outlaws ''Star Wars Outlaws'' is a 2024 action-adventure game developed by Massive Entertainment and published by Ubisoft. Set in the ''Star Wars'' universe between the events of ''The Empire Strikes Back'' (1980) and ''Return of the Jedi'' (1983), th ...
''.


Manually upgrading DLSS support

Users can manually replace the DLLs in games to support a newer version of DLSS. DLSS Swapper, an
open source Open source is source code that is made freely available for possible modification and redistribution. Products include permission to use and view the source code, design documents, or content of the product. The open source model is a decentrali ...
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.


Anti-aliasing

DLSS requires and applies its own
anti-aliasing Anti-aliasing may refer to any of a number of techniques to combat the problems of aliasing in a sampled signal such as a digital image or digital audio recording. Specific topics in anti-aliasing include: * Anti-aliasing filter, a filter used b ...
method. Thus, depending on the game and quality setting used, using DLSS may improve image quality even over native resolution rendering. 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 it can be thought of as an advanced and superior TAA implementation made possible by the available tensor cores.
Nvidia Nvidia Corporation ( ) is an American multinational corporation and technology company headquartered in Santa Clara, California, and incorporated in Delaware. Founded in 1993 by Jensen Huang (president and CEO), Chris Malachowsky, and Curti ...
also offers Deep Learning Anti-Aliasing (DLAA), which provides the same AI-driven anti-aliasing DLSS uses, but without any upscaling or downscaling functionality.


Architecture

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 accelerator A neural processing unit (NPU), also known as AI accelerator or deep learning processor, is a class of specialized hardware accelerator or computer system designed to accelerate artificial intelligence (AI) and machine learning applications, inc ...
s called Tensor Cores. Tensor Cores are available since the Nvidia Volta
GPU A graphics processing unit (GPU) is a specialized electronic circuit designed for digital image processing and to accelerate computer graphics, being present either as a discrete video card or embedded on motherboards, mobile phones, personal ...
microarchitecture In electronics, computer science and computer engineering, microarchitecture, also called computer organization and sometimes abbreviated as μarch or uarch, is the way a given instruction set architecture (ISA) is implemented in a particular ...
, which was first used on the Tesla V100 line of products. They are used for doing
fused multiply-add Fuse or FUSE may refer to: Devices * Fuse (electrical), a device used in electrical systems to protect against excessive current ** Fuse (automotive), a class of fuses for vehicles * Fuse (hydraulic), a device used in hydraulic systems to protec ...
(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 In computing, CUDA (Compute Unified Device Architecture) is a proprietary parallel computing platform and application programming interface (API) that allows software to use certain types of graphics processing units (GPUs) for accelerated gene ...
Warp Warp, warped or warping may refer to: Arts and entertainment Books and comics * WaRP Graphics, an alternative comics publisher * ''Warp'' (First Comics), comic book series published by First Comics based on the play ''Warp!'' * Warp (comics), a D ...
-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 Windows provided DirectML as one part of
DirectX Microsoft DirectX is a collection of application programming interfaces (APIs) for handling tasks related to multimedia, especially game programming and video, on Microsoft platforms. Originally, the names of these APIs all began with "Direct" ...
to support Tensor Cores.


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 1080p (1920 × 1080 progressively displayed pixels; also known as Full HD or FHD, and BT.709) is a set of HDTV high-definition video modes characterized by 1,920 pixels displayed across the screen horizontally and 1,080 pixels down the scre ...
, 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 may lead to increased input latency, as well as
visual artifacts Visual artifacts (also artefacts) are artifact (error), anomalies apparent during visual representation as in digital graphics and other forms of imagery, especially photography and microscopy. In digital graphics * Image quality#Image quality ...
. 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 resolution 4K resolution refers to a horizontal display resolution of approximately 4,000 pixels. Digital television and digital cinematography commonly use several different 4K resolutions. In television and consumer media, 38402160 (4K UHD) with a 16:9 asp ...
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 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 compatability and higher training scalability regarding future improvements.


See also

*
FidelityFX Super Resolution GPUOpen is a middleware software suite originally developed by AMD's Radeon Technologies Group that offers advanced visual effects for computer games. It was released in 2016. GPUOpen serves as an alternative to, and a direct competitor of N ...
– competing technology from
AMD Advanced Micro Devices, Inc. (AMD) is an American multinational corporation and technology company headquartered in Santa Clara, California and maintains significant operations in Austin, Texas. AMD is a hardware and fabless company that de ...
* Intel XeSS – competing technology from
Intel Intel Corporation is an American multinational corporation and technology company headquartered in Santa Clara, California, and Delaware General Corporation Law, incorporated in Delaware. Intel designs, manufactures, and sells computer compo ...
* PlayStation Spectral Super Resolution – similar technology from
PlayStation is a video gaming brand owned and produced by Sony Interactive Entertainment (SIE), a division of Japanese conglomerate Sony. Its flagship products consists of a series of home video game consoles produced under the brand; it also consists ...


References


External links

*
DLSS on the Nvidia developer website
{{NVIDIA 3D computer graphics Nvidia Anti-aliasing algorithms