Tomas Akenine-Möller

Researcher @ NVIDIA, professor @ Lund Uni, Real-Time Rendering, Ray Tracing Gems, crime fiction book: Gamla kirurgen (

[Tomas Akenine-Möller @inversepixel]

Real-Time Rendering progress!
(Note that both image and paper quality is much better in the 2nd print) @pointinpolygon @renderwonk @SebHillaire @kenpex @miwanicki

[Tomas Akenine-Möller @inversepixel]

Our upcoming HPG 2025 paper ”Collaborative Texture Filtering” is up!
Research done with
@_pandersson, Matt Pharr, and @BartWronsk.
https://t.co/ZZtPU8vkJB

[Tomas Akenine-Möller @inversepixel]

@pixelmager @NOTimothyLottes Here it is:

https://t.co/nAzRm3aEYK

[Bart Wronski 🇺🇦🇵🇸 @BartWronsk]

I'm excited to share our latest paper (work with Matt Pharr and @inversepixel ), "Improved Stochastic Texture Filtering Through Sample Reuse" accepted to I3D'2025.
https://t.co/8N9dlSdplT
https://t.co/WTtpMHfHlW 1/

[Tomas Akenine-Möller @inversepixel]

@jendrikillner Thanks for the kind words about our book! 🙏🏻

[Tomas Akenine-Möller @inversepixel]

@mwesterdahl76 @ChristerEricson I’m not on X very often any longer. Not even Mastodon. So no advice for you. Would be fun to catch up some day, though. Are you based in Stockholm?

[Pontus Ebelin @_pandersson]

FLIP v1.4 is out! It makes the Python implementation about 20-47x faster than before, and significantly more convenient to use. Code available at https://t.co/a5nWWuF2ua. Details in 🧵.

[Tomas Akenine-Möller @inversepixel]

@_pandersson

[Tomas Akenine-Möller @inversepixel]

Single header FLIP.h, for both CPU-only and CUDA, has just been released:
https://t.co/upem5dZD5m

[Eric Haines @pointinpolygon]

A Korean translation of "Real-Time Rendering" will be released July 31. See https://t.co/kvN9UQCGDY for bookstores carrying it.

[Aaron Lefohn @aaronlefohn]

We finally get to share our neural materials research.

We created custom highly-realistic reference materials, we invented new neural models, and we built new graphics systems.

End result is these neural materials run in a real-time path tracer.

https://t.co/EOHnRbjjS1

[Aaron Lefohn @aaronlefohn]

NVIDIA is thrilled to share our SIGGRAPH 2023 papers. It is our best SIGGRAPH yet, with ~20 papers authored in partnership with over a dozen universities.

Generative AI, 3D content creation, neural rendering, neural physics, and more...

https://t.co/fN6f3g2eDQ

[Bart Wronski 🇺🇦🇵🇸 @BartWronsk]

I'm super excited to finally share our work (with @karthikvnathan @marcosalvi @inversepixel @_pandersson @aaronlefohn ), accepted to Siggraph 2023: https://t.co/La6yaoB1PT Neural Texture Compression.

[Tomas Akenine-Möller @inversepixel]

@phyronnaz Sorry for the late reply. For each n_ijk, we compute the analytic normal, i.e., Eq 9-11. This is 3 bilinear interpolation times 8 corners. And then a trilinear interpolation on top of that. @SoderlundHerman

[Tomas Akenine-Möller @inversepixel]

Lookit! Lookit!

[JCGT @JCGT_announce]

Hansson-Söderlund, Evans, and Akenine-Möller, Ray Tracing of Signed Distance Function Grids. https://t.co/APZLQgxD5Y

[Tomas Akenine-Möller @inversepixel]

@knarkowicz We did not look carefully into that, unfortunately.

[yosl ber @yoslber]

Improved material & light separation in triangular 3D model extraction from images.
Paper, video & code: https://t.co/oKr5UTjKeV #NeurIPS2022, @nvidia

[Cyril Crassin @Icare3D]

The #NVIDIA ADA GPU Architecture Whitepaper is available: New RT cores with Opacity Micromaps + Displaced Micro-Meshes, 2x Ray-Triangle intersect throughput, Shader Execution Reordering, 96MB L2 cache, 2x Optical Flow accel. perf, improved Tensor Cores...
https://t.co/zy1cEq7fiy

[Tomas Akenine-Möller @inversepixel]

@marcosalvi @BrianKaris We had it as a TODO in one of our files, but did not get around to it :-(

[Tomas Akenine-Möller @inversepixel]

@marcosalvi @BrianKaris Marco is right: we did not have occupancy bits. That would have helped further.

[Tomas Akenine-Möller @inversepixel]

@BrianKaris No, we did not do that... that's clever!
We could do that even for SVS, i.e., shrink the AABB around each surface inside a single voxel (but we have not tried that either).