This is one of the best games of all time.
While out on a walk – after playing for a few hours – the pieces for how it was going to end suddenly clicked together in my mind. It felt like getting hit by a 2x4 (complimentary).
As with many CG concepts, implementations can be very different to the ref. + the ref often doesn't bother efficiency and tweaks.
For Gabor noise, a ref implem was just posted here: shadertoy.com/view/slj3W1
NB: all ingredients have been revisited here: inria.hal.science/hal-02104389
Sur fuites de données je suis 100% d’accord il y a un risque (pas plus que lorsqu’on utilise Google drive)
Pour les hallucinations, et la perte de sens je dirais que ça dépend de l’utilisation qu’on en fait…
Les syndicats avaient des utilisations en tête quand ils ont fait ces recommandations ?
-- JOB SEARCH POST/RT APPRECIATED --
Hello everyone!
I am available for work (full time position/internship) anywhere in the world with priority going to the EU, starting June 2026. 🧵
I agree, I’m still angry at some authors for blatantly faking some data.
But I feel the acceleration of publishing rate that came with ML is not helping.
A ML researcher once told me it wasn’t worth spending to much time on a method cause it’s gonna be obsolete in 6 months anyway …
That’s is actually scary !
I can’t imagine how much research time will be lost trying to replicate the results from this kind of paper …
The first image is from the aforementioned article the second is from a article published in 1995.
( inria.hal.science/inria-005888... )
I’m not saying there is no improvement here, but seriously how can you not cite texture synthesis papers ?
How can an article like this can go through a SIGGRAPH Asia review process without this being brought up ?
There are four decades of papers on the subject, can we just ignore that and do not credits the authors of those methods ?
I don’t like to publicly criticize science articles, but this work perfectly illustrate what I think is wrong in graphics nowadays : yunfan.zone/gswt_webpage/
This work is clearly doing shell map like texture synthesis, and do not cite any previous work.
The word « texture » is not even mentioned.
🌶️ Hot take: ML-based graphics makes some graphics researchers unhappy for the same reason diffusion models make artists unhappy.
Both automate the interesting and beautiful parts of the work and both deskill the worker. Both result in questionable quality and both are being adopted regardless.
It is time! 🥰🤍🤍🤍
www.kickstarter.com/projects/roz...
September 9th! Save the date!
My two Lenormands will also be available during the campaign! :D
They also tend to don’t read paper published in non us based conf, but that’s another story …
Packed this little guy up for #SIGGRAPH2025
Come to our course on Computational Craft, Wed 2-5 to see it in action!
s2025.conference-schedule.org/presentation...
Fewer, better, with less cherry picked result, and replicable with reliable open sources code
We are pleased to announce an open PhD position at the CNR-ISTI
We are looking for a motivated PhD student with a background and interest in 3D Graphics, Geometry Processing, and Machine Learning.
**Deadline: 18 July 2025**
phd-ai-society.di.unipi.it/applications/
(pag 19 of the call: AI for 3D)
Graphics Programming weekly - Issue 398 - July 6th, 2025 www.jendrikillner.com/post/graphic...
So I contacted the editor that also didn't know how to contact them.
I contacted the google search support, they also don't know how to reach scholar.
Recently google scholar wrongly attributed one of my article ot another author.
In my quest to fix the issue I discovered that their is no way to contact scholar.
(appart from a contact email that is propably redirected to /dev/null)
Hardware virtual textures look like a marvelous tool for large terrains or volume compression.
Alas, they are in a sad state in terms of performance and usability. And strangely, the (very bad) binding perfs varies a lot with the driver.
→ read here: hal.science/hal-05138369
@rcmz0.bsky.social
I know a few lab heads who are going to regret putting their name on all the paper going out of their lab 🤡
The surface mesh of a landscape (top left) is enriched with tens of millions of grass blades, designed in path traced in real time using a procedural density map (bottom left).
Triangles offer a natural strata to layout efficient non uniform random sampling on meshes. Our triangle rejection sampling reaches 10B samples/sec, which can feed primitive instancing, fiber distributions or emissivity sampling. Details in our HPG25 paper: research.adobe.com/publication/...
The source code to generate all our results is available on github: github.com/PacomeLuton/...
je mets pas tous mes œufs dans le même panier :)
and @pacomeluton.bsky.social !
Oui, il fallait bien une alternative au site de l'autre fou furieux
Holding SIGGRAPH Asia 2026 in Malaysia is a slap in the face to the rights of LGBTQ+ people. Especially now, when underrepresented people need as much support as we can possibly give them ! Angry like me ? Sign this open letter to let them know. 🏳️⚧️🏳️🌈
docs.google.com/document/d/1...
Graphics Programming weekly - Issue 395 - June 15th, 2025 www.jendrikillner.com/post/graphic...
Graphics Programming weekly - Issue 394 - June 9th, 2025 www.jendrikillner.com/post/graphic...
