Krzysztof Narkowicz

We use a similar technique in UE, but using cheap AO derived from the distance fields, which then artists use to modify materials in material shaders. Though it's much less powerful - more like a procedural scene-aware texturing than a mesh blend system.

YouTube video by High-Performance Graphics The Future of Analytical Materials in a Neural World

Amazing talk about Neural Materials. Lots of insight - from why layered materials are important to an overview of current neural solutions and their tradeoffs: youtu.be/xUnXPNFWJUY?...

My feeling is that 20y ago there was a huge barrier to start, but if you could land a publishing deal (even on Steam) your game would at least recoup a large part of the budget. Nowadays the risk is much higher.

It's very simple. One is checkerboarding and the other one is half/quater res.

Well, it's more like "Go, go, go, fuck (KURWAAA), police" :)

Great to see you getting this award and certainly well deserved!

It's designed for run time compression (e.g. real-time captured env maps), so quality isn't the best. If you can compress those offline then likely Compressonator would be a better choice.

I imagine dynamic register allocation is also quite useful on DXR 1.0, as on hit you need to evaluate materials and they can have highly variable complexity. At least in the future, as for now it seems like everyone is either simplifying or caching materials for perf reasons.

It reminds me of FMV games, which were a cool idea, but it also was a dead end due to various limitations of the tech.

Another great article from Chips and Cheese. This time about dynamic RDNA4 register allocation. Having full dynamic allocation would be huge for all those complex shaders we write nowadays, but as the article shows it's not easy to get there.

Measuring acceleration structures Hardware accelerated raytracing, as supported by DirectX 12 and Vulkan, relies on an abstract data structure that stores scene geometry, known as “acceleration structure” and often referred to as “BVH...

New blog post! "Measuring acceleration structures", in which we will compare BVH costs on various GPU architectures and drivers and attempt to understand the details enough on AMD hardware to make sense of the numbers!

Reposts appreciated :)

zeux.io/2025/03/31/m...

I see this more as a big corp opened a service which allows you to order Simpson merch without owning the IP. Yeah, a skilled artist could make such a t-shirt himself, but it's not the same as a company earning money by selling them.

Well, obviously would prefer a tech paper actually digging into tech, but still it's a nice post with some hints. Hopefully one day the embargo will be lifted.

Interesting to see a bit of details behind the amazing DLSS tech: research.nvidia.com/labs/adlr/DL...

In UE we just write out line data to a buffer and then draw those lines using the rasterizer.

VT surface catching has always been a very tempting idea, which could help with lots of things, but how do you deal with generating unique and reasonable UVs on UGC content? Some things like foliage don't seem to have a good solution.

Not sure what's the definition of PT translucency, but UE5 RT translucency does trace paths. This is how it can do multiple reflection/refraction events, where each hit needs to be lit by multiple light sources and receive GI.

Graphics Programming Conference 2024 - YouTube The Graphics Programming Conference is a three day event in November. We have keynotes from industry experts, presentations, and “masterclass” workshops with...

Graphics Programming Conference 2024 talks are up. Looking forward to learning the new Tomasz magic :) www.youtube.com/playlist?lis...

It's just a latest type of one of those weird airplane audio jacks, preventing people from stealing headphones: www.amphenolpcd.com/wp-content/u...

Nowadays you could make a good living from videos like that on YouTube :)

Does anyone know whether DoF is done through path tracing or post in offline movie rendering? I've heard that it's mostly done in post due to performance and extra flexibility, but I wonder whether that's still the case, and whether some shots are rendered (challenging DoF) and some in post.

Shipped solution uses a small runtime NN, but at the end of the talk they mentioned that they later found a faster alternative, which they call there "product fields".

Talk was amazing, but not sure if this is an example of an appealing NN application, as they came up with a better non-NN solution at the end :)

I meant barriers for hobby projects. As for the practicality and performance cost, indeed that's an issue as ML is a quite bruteforce solution. I suspect upscalers don't run per pixel ML due to cost and inability to quantize. Rather they output downscaled/quantized heuristics, which then drive TAAU.

I find that the biggest barrier is training data and compute, so it's hard to build any cutting edge stuff outside of things like Neural Radiance Caching, which learn on the fly.

It's still under heavy development, so not ready to talk about specifics yet. General idea is that it's a stochastic light sampling technique like ReSTIR DI (or Brigade real-time PT, or any PT really). The actual algorithm for sampling is different though, e.g. instead of ReSTIR it uses ray guiding.

It’s early days. Lots of ideas on P4 shelves, algorithms to try and work left. Not ready yet to talk about tech details. Still, officially the cat is out of the bag, so it’s time to buckle up and deliver on the promise. Can't wait to see the first games shipping with this tech.

2 months ago there was this crazy idea - could we dogfood the latest prototype using a demo and shape it into an experimental feature? It was quite a ride, but thanks to @tiagocostav.bsky.social joining MegaLights, help from other engineers and an amazing art team we made it.

Main goal was to make it work across all target HW, including consoles. Otherwise it would just add extra work for artists setting up another lighting scenario, and high-end GPU lighting would be constrained by content choices, which had to be made to ship on the slower hardware.

Years ago I talked to a bunch of companies at GDC and everyone was bringing up optimizing number of lights, disabling shadows with distance, light overlap... It felt like there was a big opportunity to transform their workflows, so I started prototyping ideas between other work.