Hot off the press, the GPU Zen 4! You can get yours on Amazon: www.amazon.de/GPU-Zen-Adva...
Hot off the press, the GPU Zen 4! You can get yours on Amazon: www.amazon.de/GPU-Zen-Adva...
I am happy to announce publication of my chapter titled "Real-Time Neural Network Implementation for GPUs" in GPU Zen 4 book, available now.
Chapter comes with full MIT-licensed source code, available on Github here: github.com/boksajak/MLP...
The book is available on Amazon.
Forgot to post it here, but I recently went through @boksajak.bsky.social's great Crash Course in Deep Learning. To make sure I understood everything, I implemented it in Odin.
This straightforward CPU version is very slow as you might expect, but also easy to follow.
github.com/wookie41/odi...
With interior? Is there an art gallery inside?
This is a great article about ReGIR / World-Space ReSTIR with nice improvements by Tom Clabault:
tomclabault.github.io/blog/2025/re...
See what our research teams have been up to with our latest papers:
π Joint Denoising and Upscaling via Multi-branch Network.
π Cardioid Caustics Generation with Diffusion Models.
π Geometric Integration for Neural Control Variates.
π₯ View here: gpuopen.com/learn/public...
New blog post! Behind the scenes of some of the techniques involved in making our last PC demo π« gboisse.github.io/posts/this-i...
I love to plqy games with ambient occlusion only π
One group is stochastic friendly to ray tracing while the other group is more suited to rasterization pipeline. I agree though that over time, stochastic RT approaches will universally be the high end option
Graphics Programming weekly - Issue 413 - October 19th, 2025 www.jendrikillner.com/post/graphic...
I have been coding in C++ for 26 years, but I admit I cannot read what this does π€¨
A comparison between AMD Neural Light Sampling and ReSTIR.
Get up to speed with our latest advanced graphics research:
π GATE (Geometry-Aware Trained Encoding) for neural rendering.
π Real-time procedural GPU tree generation.
π Neural Visibility Cache for real-time light sampling.
π₯ Download the papers: gpuopen.com/learn/public...
Our "Neural Visibility Cache" paper has been published in JCGT! Here is a link: www.jcgt.org/published/00...
I found it cool to hear the motivation for High-Frequency Learnable Encoding for NRC\NIRC\Neural Ambient Occlusion from the perspective of Kernel Machines!
Classics π
I will be presenting our "GATE: Geometry-Aware Trained Encoding" at HPG on Wednesday at 9:50AM. See you all in Copenhagen soon! Paper link is here: diglib.eg.org/bitstream/ha...
I'll buy your book
This is the kind of story I needed to hear today π. The power of mexican cuisine πͺ
Just a good balance for performance. Feel free to try larger networks, but tou may need to increase number of features per level of the hashgrid as well
(1) Yes, we mention that as "clustering" for future work
(2) We could have a fixed MLP serving as a decoder, or non-neural function reading stuff stored on geometry with GATE.
New papers day! Preprints of our βGATE: Geometry-Aware Trained Encodingβ to be presented at HPG and βNeural Visibility Cache for Real-Time Light Samplingβ currently on Arxiv are available here:Β boksajak.github.io/blog/Preprin...Β Kudos to co-authors Daniel Meister and Carsten Benthin. Enjoy!
Lol, and you need to use the advance lever to move the "film" to the next frame. Perfect for people who want the inconvenience of using film with none of the benefits. I am glad it exists and that I don't have to use it.
You're within the order of magnitude of quarter res still. We can agree
I received a patent trophy! Big thanks to my friends and colleagues who helped me along the way!
Started putting together a new toy gfx framework based on python with pybind11 for directx12 etc.
as a hotfix: Try doing some programming with a truly horrible languageβ’οΈ and/or platform few decades old and suddenly the modern tools will look like a blessing.
For a while at least. YMMV
After many weeks of effort I finally have radiance on screen now! Iβve still got issues mostly related to my Surfel Acceleration Structure, however Iβd say the results are already looking quite promising. It has kind of a hand painted look to it now :)
New blog post: Relativistic Quaternions
I briefly discuss what quaternions and dual quaternions must become in spacetime in order to represent physically meaningful motions.
terathon.com/blog/relativ...
yes, you cast one more shadow ray, but you may be able to forgo casting the same shadow ray second time for shading when the selected light is the same as initial candidate
Want your BRDF to be environmentally friendly? Here's a terrible option to keep semi-metals energy conserving
www.zyanidelab.com/semi-metalli...
I liked the AntTweakBar. Not sure if that's still around