DLSS 4.5 Ray Reconstruction is a definite improvement but path traced fidelity is still not a 100% solved issue

Posted by:
Oz Travolta
Posted on:
August 25, 2026
Category:
BlogBlog
System:
Unknown
Price:
USD 0

Nvidia‘s new DLSS 4.5 Ray Reconstruction feature is laser-focused on trying to fix the second most annoying thing about ray traced or path traced games: visual artifacting. Yes, the lighting effect does deliver the most accurate-looking lighting and shadows in games, but in motion there is a definite visual weirdness added into scenes. And that weirdness generally comes from the denoising pass designed to turn the low-fidelity path traced image, with its limited number of rays, into a fully realised frame.

Leave a game’s viewport still and the scene will pretty rapidly come together to make a sharp, convincing image. Shift that around, or have that scene filled with moving objects or characters and you’re going to see the sort of visual trails you might only have been used to in the warehouse parties of your early twenties. Just me?

The issue is that it’s way too expensive in terms of raw compute to trace every single photon/pixel that would otherwise make up a fully traced scene. Even with the current method of tracking a far smaller representative sample of rays bouncing around the geometry of your game world it’s still incredibly demanding of your PC’s hardware.

This is, by the way, the most annoying thing about ray traced or path traced games: the amount of graphical horsepower the tech demands over pre-baked lighting techniques. The huge performance hit it involves is punitive for all but the most powerful GPUs, and we are still no closer to solving that right now.

So we still have to use small numbers of tracked rays to create an approximate scene which looks something like this:

Nvidia DLSS 3.5 Ray Reconstruction — (Image credit: Nvidia | CDPR)

But that doesn’t look great if you’re trying to make a convincing world, though I guess there’s something to that aesthetic in a sort of 3D ASCII kind of way. Anyway, to realise this image into a production ready frame you need to use a denoiser to fill in the blanks between the sampled rays, and the hand-tuned denoisers track and group pixels across multiple frames, to give them access to more samples. They then use these neighbouring pixels to interpolate and blend the scene together.

As I said, that’s fine for a static image, but those pixels don’t stay representative for long and in motion they break down, adding in artifacting to a scene and smearing detail away from textures. This is where the original Ray Reconstruction feature came in, replacing the hand-tuned denoisers with an AI-based denoiser working alongside Nvidia’s upscaling models, to generate more accurate pixels in between those sampled rays.

And now we’re finally getting an updated version of Ray Reconstruction which uses the sharper second-gen Transformer model initially brought into DLSS 4.5 Super Resolution back in January.

Image 1 of 2

Nvidia Ray Reconstruction — (Image credit: Nvidia)

And it’s about time, because for ray or path traced games, even if you were using the improved transformer model of DLSS 4.5 Super Resolution, Ray Reconstruction was still using the old model, leaving you those tell-tale artifacts.

Nvidia is touting four main improvements with DLSS 4.5 RR:

Efficient Denoiser: The new model delivers 35% more compute capability, and processes 20% more parameters, while maintaining similar performance to the previous model.
Enhanced Super Resolution: Building upon the advances from DLSS 4.5 Super Resolution, the model has deeper spatial awareness across every scene, and more intelligently uses game engine pixel sampling and motion data. The result is improved lighting accuracy, better temporal stability and clearer motion in ray-traced and path-traced content.
Expanded Training Dataset: Trained on a larger dataset, the new model is even better at image reconstruction. This intelligence gives the model even better awareness to pick the most accurate engine data to reconstruct scenes closer to ground truth.
Finer Developer Control: The new model provides developers with finer control for temporal accumulation, providing precise tuning of model response for even better image quality.

The new version of the feature is releasing today, and jamming the second-gen transformer model into supported games is done via the Nvidia App rather than from inside your games’ settings screens. You just need to select a title from within the Nvidia App itself, navigate to the ‘DLSS Override – Model Presets’ entry and select ‘Preset F’ from the ‘Ray Reconstruction’ dropdown menu. Apply it and you should be set.

Swipe to scroll horizontally

DLSS 4.5 Ray Reconstruction supporting games
Alan Wake 2	EVERSPACE 2	NTE (Neverness to Everness)
Avatar: Frontiers of Pandora	F1 25	Portal with RTX
Backrooms: Escape Together	FBC: Firebreak	PRAGMATA
Call of Duty: Black Ops 7 (Coming August 20th)	Half-Life 2 RTX	Resident Evil Requiem
Crimson Desert	Hogwarts Legacy	Samson
Cyberpunk 2077	I Am Jesus Christ	Star Wars Outlaws
Death Relives	Incursion Red River	Subliminal
Directive 8020	Indiana Jones and the Great Circle	Sword of Justice
DOOM: The Dark Ages	Marvel’s Spider-Man 2	The First Descendant
Enlisted	NARAKA: BLADEPOINT	War Thunder

While complete image fidelity across all ray or path traced games is by no means a 100% solved problem, it’s clear that DLSS 4.5 Ray Reconstruction is able to deliver a more stable image when it’s in use. And it’s not just about giving you a more stable image with less ‘boiling’ textures and trails, either, it’s adding back in more detail to a scene that would have otherwise been lost.

You can see that especially in the below video for Resident Evil Requiem’s opening scene. The textures on the white car at the beginning are still shimmering behind the rain effects using the older model, but are almost entirely stable with DLSS 4.5 RR enabled. But it’s the extra detail on the ground that highlights what the new second-gen transformer model is capable of here.

DLSS 4.5 Ray Reconstruction on left, DLSS Ray Reconstruction on the right

Of course we’re going to highlight what it looks like in Nvidia’s poster child for all things DLSS: Cyberpunk 2077. In the two videos below you can see where that extra temporal stability really makes a difference. In this first video, inside a store, you can see the striping on the ground as the viewport shifts, which is completely absent from the improved DLSS 4.5 RR version.

You might have to watch it loop through a couple of times to see what I mean, but if you focus on the older version on the right you will see, when the view moves to the floor, that there is an after image of essentially the edge of the screen imprinted on the floor. This fades quickly, but is noticeable.

DLSS 4.5 Ray Reconstruction on left, DLSS Ray Reconstruction on the right

Outside, looking up at the ceiling of this underpass you can see where the textures resolve far, far quicker than before. The different areas of the ceiling using the previous version of RR almost seem like they can’t make up their mind what they should look like, while DLSS 4.5 RR comes in with far more certainty.

DLSS 4.5 Ray Reconstruction on left, DLSS Ray Reconstruction on the right

My final example comes from Alan Wake 2 and its own heavy use of path tracing and the denoising steps that are vital to the game’s fidelity. To be honest, the strange artifcating of Alan Wake 2 almost gets a pass from me, because the dreamlike trails around people kinda add to the weirdness of the game. But it’s not meant to look like that.

You can see from the dancing man in the Elderwood Palace Lodge bar that those trails are almost entirely gone from the latest version of Ray Reconstruction. But, notably, they are not completely resolved. There is still some level of artifacting around his feet as he shuffles around the wooden floor.

Though it is worth noting here you can also see the enhanced level of detail the second-gen transformer is adding back in. If you look to the wooden floor in the room behind the dancing dude you will see the planks are more clearly represented.

DLSS 4.5 Ray Reconstruction on left, DLSS Ray Reconstruction on the right

So yes, there is still some work to be done before we can say that path tracing visuals have been perfected, but this is still a worthy upgrade. And honestly, we probably need a mixture of both improved AI modelling and more powerful hardware to be able to add more traced light bounces into a frame. But in these tech-starved times of ours, hoping for more horsepower when the datacentres want to jealously hoard all the compute for themselves is a fool’s game.

But DLSS 4.5 Ray Reconstruction is a definite improvement over Nvidia’s previous versions. Sure, a lot of the improvements are only really telling when you’re specifically looking for them, but equally some of that smearing and the ‘boiling’ textures are absolutely things I can do without.

Ray Reconstruction also remains RTX agnostic in that it will function across all generations of GeForce RTX GPUs, and isn’t really any more draining upon your PC’s resources than the previous version. Though, as a whole, it remains true the transformer-based DLSS features weigh more heavily upon your system’s performance on older generations of RTX hardware than the RTX 50-series.