Regardless, it looks like it’s here to stay, launching on September 3rd and making its way to NBA 2K27 to bring a level of photorealism to the game that’s been out of reach for developers due to performance limitations of the hardware and software. Generative AI could be the tool they need to overcome those obstacles and bring that realism to athletes like Cade Cunningham, who got a special mention in the announcement among others.

It’s even bringing improvements to courtside NPCs and spectators, while allowing RTX 5090 owners to run the game in 4K at a whopping 370 frames per second. The accompanying summary of how DLSS 5 works is interesting to read and should help arm you with more knowledge before you wade into the sea of opinions around the tech.

As for NBA 2K27, it launches on September 4th for PC, PS5, Xbox Series X/S and Nintendo Switch 2. Check out our feature for everything you should know.

The trailer showcases how Tides of Annihilation can look on supported hardware if players enable path tracing and DLSS 4.5. Unlike Nvidia’s typical “RTX On/RTX Off” style of videos, we don’t get helpful side-by-side comparisons of the same scenes. All of the scenes are instead shown only with RTX enabled. These visuals all look incredibly detailed, with the area’s lighting playing a major role in establishing the mood of the scenes.

We also get to look at the previous trailer’s boss fight, but with RTX enabled. All of this boss’s magical abilities are at full display, especially in terms of how these magical beams play with the lighting of the scene. The system running Tides of Annihilation with RTX enabled is also likely making heavy use of DLSS 4.5 to ensure that frame rates remain stable and the player doesn’t suffer from stutters and frame drops.

Tides of Annihilation was unveiled all the way back in February 2025, and since then, developer Eclipse Glow Games has continued to release new trailers and reveal new details about the title. The most recent one from earlier this week gave us a deeper look at the game’s story, and the developers also explained details about the Knight system, which will enable protagonist Gwendolyn to switch up her gameplay style.

Among the Knights showcased for this was Lancelot, who focuses on fast-paced swordplay and gives Gwendolyn new tools to rush into groups of enemies and even some defensive options for when she gets stuck in a bind.

The story of Tides of Annihilation has been described by the studio as being its own take on the classic Arthurian legend. Rather than simply recreating the same narrative, however, the studio instead decided to tell its own story that revolves around a regular person, Gwendolyn, who lives in the modern age and finds herself stuck in an invasion from another dimension.

While Gwendolyn starts out the story being understandably scared of the horrors taking place around her in the new world she finds herself trapped in, she eventually finds some friends and allies, all of whom encourage her to become a warrior capable of commanding the knights and eventually even bring an end to the war.

Gameplay in the trailer was noted as being from the middle of the game. This means that the studio got to show off just how intense the combat in Tides of Annihilation could get. However, the developers also confirmed that, when it comes out, the intensity of combat in the game will be gradually ramped up as players start getting stronger, and that it won’t be this intense right from the beginning.

Tides of Annihilation doesn’t yet have a release date, and the developers have said that they are working hard to finish it. The game is being made for PC, PS5, and Xbox Series X/S.

RTX is also supported, though it’s to support Lumen and MegaLights, and Reflex will ensure low latency. Which may not matter all that much in Campaign but should be worthwhile in Versus. That is, after the development team is ready to outline all the changes coming in the 4v4 format.

Of course, those who pre-ordered E-Day or subscribed to PC Game Pass can experience all of the above when the open beta goes live on August 6th. It’s likely multiplayer-only, so expect more details on maps, modes and other changes in the coming weeks. Who knows? We may even see the inclusion of the new Horde Siege.

Gears of War: E-Day, meanwhile, launches on October 6th for Xbox Series X/S and PC alongside Game Pass Ultimate and PC. With a Campaign that’s over 14 hours long and a reported budget upwards of $400 million, it’s certainly one of Xbox’s biggest bets, especially after making it console-exclusive. For more details, check out our feature here.

DLSS Ray Reconstruction is a tool that can be used in games to improve visual quality and frame rates without having to rely on hand-trained denoising techniques. The technology makes use of neural rendering and is available on all of Nvidia’s GeForce RTX graphics cards. The latest iteration of the tech has been trained on Nvidia’s own supercomputers and is capable of generating higher-quality pixels in parts of ray-traced frames that are typically noisier due to rays not being sampled.

Ray Reconstruction’s latest iteration is able to unify denoising capabilities along with DLSS Super Resolution into a single model, bringing in efficiencies as it analyzes temporal and spatial engine data to create sharper and more stable images while maintaining high fidelity visuals. The new model is equipped with an efficient denoiser that provides 35 percent more compute capability and can process 20 percent more parameters without missing a beat in performance compared to the previous model.

Along with this, it also builds on the upgrades that are coming to RTX GPUs with DLSS 4.5 Super Resolution, with the model having deeper spatial awareness in every scene. This allows it to be more intelligent in how it uses a game engine’s pixel and motion data for sampling purposes. Thanks to this, it can offer more accurate lighting and better temporal stability, along with clearer and smoother motion for ray tracing and path tracing scenes.

At launch, Nvidia has confirmed that DLSS 4.5 Ray Reconstruction will be capable of running in 27 games, including Everspace 2, Alan Wake 2, Crimson Desert, Cyberpunk 2077, DOOM: The Dark Ages, Directive 8020, Star Wars Outlaws, Indiana Jones and the Great Circle, Pragmata, Resident Evil Requiem, and Hogwarts Legacy, among others.

Features for DLSS 4.5 were first unveiled back in January, with Super Resolution leading the pack in terms of release. At the time, Nvidia had also confirmed that there would be other features and enhancements under the same umbrella, including Dynamic Multi Frame Generation, which is capable of offering a 6X multiplier over previous versions of Multi Frame Generation, which itself could go up to 4X.

Alongside offering smoother frame rates, Dynamic Multi Frame Generation is also capable of offering better synchronization between a user’s graphics card output and their display. Essentially, additional frames are only generated when they are actually needed and if the display can actually support them. This means that, if a user’s display runs at a refresh rate of 144 Hz, Dynamic Multi Frame Generation won’t overshoot that limit at the expense of other performance considerations.

Many of the features in DLSS 4.5 are powered by a new transformer model that was trained on an expanded dataset over its predecessor.

For more on DLSS, check out some of the controversies surrounding the next generation of the technology – DLSS 5.

One example is the Giant Knight that protagonist Gwendolyn encountered in the first trailer. To help improve performance, Unreal Engine China technical director Wei Liu says they conducted tests for CPU/GPU bottlenecks. It has since reduced computational overhead and raised the average frame rate. Of course, the collaboration has also ensured that Nanite can be used in-game for “automated collision and shadow optimization.”

The overarching result is that even if a Giant Knight is in the background, it will retain the same high-quality textures and fluid motion without any performance hit. And while Eclipse Glow previously announced support for DLSS and Path Tracing, it’s also communicated with Nvidia for “detailed performance analysis.” The two will also work together on “joint optimizations at the driver level” in the future. And if that wasn’t enough, parent company Tencent also provided technical assistance, though further details weren’t shared.

For those itching to play the game, a hands-on event has been announced for this Summer with registration open to all players. You can expect more details through the developer’s socials, so stay tuned for updates.

Mishima and Hsu revealed that the implementation of path tracing directly into RE Engine was handled by Capcom’s Kenta Nakamoto and Kosuke Nabata, and that it took them a year and a half to accomplish. The system seemingly makes use of Nvidia’s DLSS Ray Reconstruction technology to help with denoising, and was noted as being important to make sure that real-time performance was acceptable. Unfortunately, this also had the side-effect of making path tracing in Resident Evil Requiem and Pragmata exclusive to Nvidia’s RTX graphics cards.

The speakers also noted that a number of design choices were made so that Capcom could make use of streaming RIS, which could pick the most important light sources to which path tracing could be applied, all while remaining efficient. These design decisions include the compensation of brightness so that scenes with spotlight-based lighting wouldn’t suffer from darkening artifacts, the use of Lambertian diffuse with single-lobe specular instead of the full bidirectional scattering distribution function (BSDF), the exclusion of image-based lighting, and the addition of emissive polygons.

As for DLSS Ray Reconstruction, Capcom made use of the technology to fix visual artifacts that could arise from subsurface scattering, frosty and blurry glass surfaces, and refracting surfaces like raindrops, among other things.

Leading up to their respective releases, both Resident Evil Requiem and Pragmata got trailers for their PC versions, showcasing how path tracing could bring in massive changes to scenes thanks to more realistic lighting that was only possible using RTX graphics cards. Along with this, the trailers also made sure to showcase other RTX-related benefits, including DLSS 4 and its Multi Frame Generation, which could help boost frame rates by making the GPU generate extra frames between the game’s own outputs.

As for other qualities of the games, both Resident Evil Requiem and Pragmata have been reviewed quite positively, which means that Capcom has been on quite a solid run when it comes to releasing high-quality games. Resident Evil Requiem is available on PC, PS5, Xbox Series X/S, and Nintendo Switch 2. Pragmata is slated for release later this week—on April 17th—on the same platforms.

While you wait for the release of Pragmata, take a look at its most recent trailer, where Capcom showcased how protagonist Hugh can make use of his arsenal of weapons alongside android Diana as they make their way through The Cradle. The default weapon available to Hugh is the Grip Gun, which essentially acts as a pistol of sorts. When it’s time to deal more damage, however, Hugh can get his hands on the Shockwave Blaster, for example, which can help him attack multiple foes at the same time.

However, it is worth remembering that Hugh’s weapons aren’t the only thing you’ll need to use. Enemies in Pragmata have high defences, and you will need to make use of Diana’s hacking abilities to make them lower their guard.

In case you missed it, we really liked Pragmata in our review, scoring it a nine out of ten for its innovative fusion of combat and puzzle-solving. However, those same elements may also prove a tad divisive if you go in expecting a straightforward shooter. Either way, the one thing we’re sure you’re going to love is the game’s excellent visuals and a unique art style that pops with colors as its levels and bizarre, homicidal bot enemies spring to life.

This is especially apparent during combat when attempting to hack your way past enemy defenses, even as you’re tasked with evading their attacks and managing the space around you. We already anticipated the combat being among the game’s best features, but the visuals, especially on high settings, do give it a run for its money.

In its full GDC 2026 session outlining the future of Path Tracing, Nvidia’s Martin Stich talked about how one non-gameplay scene (based on assets provided by CD Projekt RED) featured 60 million plants and one million trees across a 5×5 km terrain. Despite featuring 200 different plant species and some trees having more than 10 million polygons, it loads without any streaming.

All of this is complete with fully path-tracing lighting. Perhaps the most impressive part of all this is that it runs at 4K/80 FPS, but there are some caveats. It’s running on an RTX 5090, and the 4K resolution is upscaled from 1440p with DLSS Quality mode. Comparatively, an RTX 4070 would eke out 58 frames at 1440p (upscaled from 960p).

As noted previously, none of this represents the actual gameplay or the hardware you’ll need to run The Witcher 4 on PC. At this point, it’s a cool tech demo of what RTX Mega Geometry is capable of using the game’s assets. Whether it reaches this level of fidelity and complexity remains to be seen, so stay tuned.

The Witcher 4 doesn’t currently have a launch date, though there are claims of a late 2027 launch. Officially, it’s still in full production with CD Projekt RED recently scaling up its team (among others) for the same.

“I can imagine in the future devs will be able to train this tech for particular art style or specific people faces and it might replace expensive raytracing etc.,” he wrote. “This is just a little uncanny beginning. No way haters will stop this. It’s way more than a soap opera effect every tv has when you turn motion smoothing on.”

It is worth noting that this is far from the first time Vávra has said positive things about AI-based technologies. Back in December, he took to social media to discuss how “AI hysteria” has been getting out of hand in light of at-the-time discussions about the role of generative AI in game development.

“I’m no fan of AI generated art, but anyway, it’s time to face reality,” wrote Vávra. “AI is here to stay with us. As frightening as it may be, that’s the way it is. Personally, it scares me the most in the music because you can’t even recognise AI there anymore.”

Vávra went on to discuss potential use cases of generative AI tools, which have the potential to remove some of the more tedious aspects of game development. He brought up things like having to “spend 500 hours in the studio recording completely generic heckling and generic bars.”

“If AI can help me make an epic game in a year with a smaller team like in the old days, I’m all for it,” he wrote. “That game will still have an art director, writers, programmers, graphic designers, but they won’t have to do the tiresome and boring tasks, they’ll have to focus on the essentials. I have ideas for lots of games, but I’m fifty years old and so far it’s taken me seven years on average to make one game. If AI helps me realize those ideas faster, I’m all for it.”

On the other hand, DLSS 5 has faced criticism from many other game developers. Among these was veteran animator on games like God of War Ragnarök and Death Stranding 2: On the Beach, Mike York, who noted that “this isn’t just some lighting.”

“No, no, no, no, no, no, no, no, no, no,” he exclaimed while analyzing the Resident Evil Requiem showcase. “No. This isn’t just some lighting, dude. What the f–… I’m telling you, this is like a complete AI re-render.”

“Who even is that? That’s a different girl,” York continued. “You know why I can tell […] – look, her eyes are no longer looking, like, correctly. That one eye is looking over here, and one eye is looking there. And it rendered the eyes differently. And you can also tell that it’s… how do I say this… it has somehow put wrinkles into her lips that weren’t there before… it’s added all kinds of details that were not there before.”

“They’re literally re-rendering this completely, frame by frame. You’re no longer looking at the game anymore, does that make sense? This is scary.”

DLSS 5 is slated for launch later this year for Nvidia GeForce GTX 50-series graphics cards. Take a look at how Nvidia CEO Jensen Huang has been defending the technology. Also check out how developers and artists from Capcom and Ubisoft were left in the dark about the showcase.

Well, that’s just what we’re here to do as we dive in to what’s good and what’s not about DLSS 5’s AI-powered upscaling abilities, and give you our opinion on whether the latest iteration of a feature that’s been around for a while is going to take away the autonomy of developers who use it.

We’re looking beyond the memes and mockery on what was supposed to be a major leap in graphics for modern games, but instead devolved into a PR disaster that NVIDIA would rather have avoided. But as things stand, the company could have done better to introduce it in a way that didn’t automatically cause derision and distrust. How, you ask? Join us and find out.

The Basics

Let’s get done with the basics first. In this section we will talking about what we know about the situation, gamers’ reaction and Nvdia’s response. So, what is DLSS5? An abbreviation for deep learning super sampling, DLSS 5 is merely the latest iteration of NVIDIA’s real-time neural rendering model that’s quite handy when it comes to enhancing lighting and materials in games. It reportedly includes a suite of controls that make things easier for developers to ensure that a game’s artistic vision is properly implemented, allowing for artists to decide on important parameters in the scenes they are trying to create.

It’s the artists who ultimately decide where and how it’s applied, and it isn’t being pitched as a one-click beauty filter as many of us have been led to believe by the outrage over its implementation in showcases.

With that out of the way, let’s dive into the heart of the controversy: reports that DLSS 5 is trying to override developers and artist’s vision for the games they work hard to create.

It’s crucial to address why DLSS 5 has gamers worried about the new tech. Some believe that the tech is going to be forced into modern games against the wishes and visions of their creators. That’s apparently not the case, and NVIDIA has been quick to try addressing that particular facet of the conversation.

It has since clarified that it is the studios who retain control over its implementation, a position further reinforced by a supporting assertion from Bethesda who have since argued in favor of it. It’s going to be under the control of artists and creators, and completely optional for players. That’s all well and good, but what has caused the tech’s reveal to draw the ire of such a huge chunk of the gaming community?

Well, that might be on NVIDIA, and it’s decision to showcase the tech in action on games that were already widely known and recognizable by the public. Take the widely circulating photo of Grace in Resident Evil Requiem, for instance. We must admit she did look quite different from her appearance in the game, and the same can be said for showcases in other games like Starfield and Hogwarts Legacy.

The adverse reactions to DLSS 5 didn’t come from abstract white papers on what the tech could do, or related SDK documentations. They came from noticeable shifts to lighting, faces, and tone in games that they knew and loved, their emotional bonds to their experiences coming into conversation with worries about AI and its implementations in modern gaming. It came across wrong, looking more like AI-fuelled restyling rather than developer-focused enhancement.

In its eagerness to show off just how good DLSS 5 could be, and the advantage it would give developers as they made new titles, NVIDIA failed to duly consider an important facet of keeping its fan base engaged: trust.

NVIDIA’s fervor to unveil a piece of tech that probably comes with benefits (which by the way isn’t clear yet) failed to properly address concerns that are rooted in a deep mistrust of AI, and its documented impact on development processes in video games.

In a world where layoffs due to AI implementations already have people on edge, the question of whether audiences can trust neural rendering software to serve the vision of its developers comes into play, and it’s one that NVIDIA should have accounted for. Previous iterations of DLSS haven’t whipped up a debate as fierce as this one, after all, even though there have been conversations about upscaling, frame generation, and ghosting in the past.

Somehow, DLSS 5 has raised the issue of aesthetic ownership, and has made players wonder about how the tech could gradually reshape games into experiences that are far removed from what they were originally intended to be. And the tech’s rollout might have just made things worse.

We’ve already spoken about how showcasing it in games that players were already familiar with invited ridicule and criticism. Those before and after comparisons are all over the internet now, and it’s easy to see why there would be concerns about the tech overriding what a studio originally intended for a game.

NVIDIA’s no-holds-barred approach to defending the tech is another factor. While they can probably see where they were coming from in his assertion that the criticisms levelled against DLSS 5 were “completely wrong”, but from a personal, more emotional note, their arguments conveyed a dismissive attitude towards what players believed were valid points they were making against a feature that they believed would take value away from the games DLSS 5 was meant to enhance.

It’s a good idea to look deeper at both sides of this argument at this junction.

The Two Sides

Let’s start with what DLSS 5’s critics are saying about it. These are all valid complaints, starting with concerns about the tech homogenizing different games across genres, giving them an AI-powered look that could be seen as a way to impose NVIDIA’s own ideas about how a game should look over the artistic visions of the studios that create them.

In the case of Grace from Requiem, the tech seemed to completely change her look, giving her a sort of “exaggerated” glow-up that seemed far removed from her look in the actual game. It further reinforced fears that the tech could make games look like what NVIDIA dictated they should look like considering that it owns the software.

Nvidia’s defense might not have addressed those fears satisfactorily enough, but the reports that it was a controllable and deterministic tool that was going to operate off of a game’s own 3D framework shows that DLSS 5 is far more than a sort of black-box beautification filter,

It’s more of a way to grant developers generative control at the geometrical level as opposed to a post-processing filter that operates on the frame level. However, all of these important nuggets that lend credence to Nvidia’s defense have been overridden by their apparent blunt dismissal of valid concerns.

Bethesda, who took on a more placatory position, by asserting that the tech was still in its early stages while also reiterating that it was a tool that left control of its implementation completely in the hands of its developers.

In Bethesda’s response to the entire DLSS 5 episode, there was one simple component that stood out. As a studio that has earned the goodwill of its fans over the years (and badwill recently), it seemed far better poised to attempt assuaging their fears. Whether it worked is a different topic altogether.

Which brings us to our own position on the subject.

Striking A Balance

We believe NVIDIA’s demo strategy should have accounted for concerns about AI taking over the creative vision of games that it’s powering, no matter how sensible those concerns were. In failing to do so, it created the situation it now faces.

But that doesn’t mean that reports about the tech taking visual control away from developers shouldn’t be taken as seriously as they have, especially in the light of public statements to the contrary. We’re not saying there’s no reason to be wary, because there absolutely is. The current demos do an absolutely pathetic job of enhancing the games, thereby destroying the art style of those products. On the other hand, let these companies deliver actual real time implementations in games running on retail platforms first. We’ll be in a much better position to judge the results then.

And the whole thing needed a bit of nuance from Nvidia. Is it that hard, Nvidia? The tech exists, and reportedly it’s quite flexible as things stand. The onus is now on NVIDIA to ensure that its true potential comes across in a way that’s able to convince us gamers, and the best way to do that is to show us what it looks like when it’s fully utilized by talented studios in the final release build of an excellent game, rather than static moving screens which look like AI face filters.

Note: The views expressed in this article are those of the author and do not necessarily represent the views of, and should not be attributed to, GamingBolt as an organization.