I've seen many questions about the platform it runs on. As the first author of the paper, let me clarify: All the demos run on a consumer PC with an RTX 4090 and a Ryzen 5950X. Additionally, the method supports both rigid body dynamics and fluid dynamics.
@shadid5167 ай бұрын
You are an author? Congrats, this was awesome!
@dfcho7 ай бұрын
Your work is amazing, and still just a PhD candidate? Can't wait to see your future papers!
@underpowerjet7 ай бұрын
This is truly amazing work.
@ihzakarunia24087 ай бұрын
Massive respect 💫
@r.m81467 ай бұрын
👏👏👏👏👏👏👏
@test-uy4vc7 ай бұрын
What an elastic time to be bounced alive! 🎉
@test-uy4vc7 ай бұрын
These simulations are getting out of hand!
@Mertiven7 ай бұрын
🤨🤨
@Nulley07 ай бұрын
What a time to be jiggly
@test-uy4vc7 ай бұрын
@@Mertiven 😂
@cvspvr6 ай бұрын
hold on to your armadillo
@pardismack7 ай бұрын
Blender desperately need to integrate this
@KeXous7 ай бұрын
just what was on my mind all the video
@theneonbop7 ай бұрын
I was thinking BeamNG, IDK but I doubt it would be impossible to add plasticity into this BeamNG's physics has a very low mesh resolution, and unstable enough that it really sounds like a pain to work with
@JustfknBill7 ай бұрын
I'm undereducated on how software works.. Do they need an AI to do this? And if so, wouldn't there be a way to p2p train it through the open source network? And if so, then why tf do we need these manufacturers? (I know physical systems somewhat well so if you can compare to physical stuff that would be amazing!)
@theneonbop7 ай бұрын
@@JustfknBill not ai, just a good technique. And people want it integrated into blender as blender’s system is comparatively outdated and slow.
@pardismack7 ай бұрын
@@JustfknBill as far as I know, some software start with a good library written by the developers that allows them to do things that other software can't, and build their product around that. Autodesk is famous for acquiring these software to get their technology and then shutting them off. There are also companies that specialize in making kernel libraries to be integrated in other software, and they sell them the license to use that technology. These deals are usually extremely expensive, as developing such libraries requires decades of work from a team of people who are both very good at advanced mathematics and computer science, and there's probably a handful of people who would qualify. Software that use these licenses just can't be free. I believe these papers are open-source, but I don't know. if they are open-source, then any software company should be able to add them in without any fee. It still probably requires some extensive programming, but the hard part is done.
@Ken1171Designs7 ай бұрын
For those not familiar with the topic, things took DECADES to get to this point where elastic simulations of this kind now take seconds per frame, even when involving millions of collision calculations. The typical physics solver would rather explode than to even finish the simulation, and potentially take HOURS to calculate it. That's why this is impressive, so it's important to first put things in perspective. 🙂
@el-_-grando-_-_-scabandri7 ай бұрын
pls forgive my ignorance, but when this will reach ... humm ... 60/120 fps? and when it will be implemented in offline singleplayer games?
@Personal43546hf7 ай бұрын
Wow impossible to guess it might happen within 5 years😊
@Ken1171Designs7 ай бұрын
@@el-_-grando-_-_-scabandri Maybe 2-3 papers down the line? But looking at the existing physics solvers, a couple of seconds per frame with millions of collisions is totally unheard of. Just by itself, this is extraordinary. Like I said above, we have to put this in perspective. ^^
@matthewe38137 ай бұрын
@@el-_-grando-_-_-scabandri It can already reach that, just not with the millions they are showing in the video, if you were to scale it down to tens or hundreds of thousands, then it would probably take less time
@ankachen74687 ай бұрын
@@el-_-grando-_-_-scabandrifor sims with smaller scales (I mean with 100k vertices, it's already in real time)
@nicks47277 ай бұрын
I love it when it's not reliant on AI, feels like we actually discovered a new technique instead of using a very very cool hammer to solve all our problems
@GinnyGlider7 ай бұрын
Lol, love the analogy. It's *almost* how machine learning works. 😄
@Wobbothe3rd7 ай бұрын
You still haven't learned the Bitter Lesson, I see.
@wobbers997 ай бұрын
Yes, that is exactly how i felt.
@ELA_ONE7 ай бұрын
This jiggle physics will have good applications, of course, for educational purposes 🍑
@Roberto-nb5cb7 ай бұрын
thicc squishy jelly a.. 😍
@emo-55617 ай бұрын
@@Roberto-nb5cbbigger please 😂
@tiagof8577 ай бұрын
In Stellar Blade 2 hopefully :)
@andydataguy7 ай бұрын
I was searching the comments for project ideas. Looks like we found a winner. Obviously strictly for research purposes 🎂
@darklord61387 ай бұрын
*Men of culture, we meet again.*
@rallicat697 ай бұрын
SIR IM HOLDING ONTO MY PAPERS VERY HARD
@Krmpfpks7 ай бұрын
SIR I AM SQUEEZING THEM
@dorianrustik68807 ай бұрын
Your enthusiasm is incredibly contagious!
@dolcruz68387 ай бұрын
Would love to see the new paper by Anthropic, it's really interesting: "Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet".
@robertstevensii40187 ай бұрын
Two Minute Papers: "They learned how to pack 1 million people into a tiny teapot" Blackrock: "Write that down! Write that down!"
@GinnyGlider7 ай бұрын
Károly: "Let's flatten this poor little armadillo" The little armadillo: Yes?
@keithdow83277 ай бұрын
Thanks!
@Sekir807 ай бұрын
No AI here? Wow! I almost lost my papers not holding onto them enough!
@RafaelSanchezBcn7 ай бұрын
Soon we will be able to design a whole universe, where the creatures who live in it will think that they are real and will not have a clue about their origins.
@britishempires7 ай бұрын
Its already happened.. we are the creatures 😂
@andrewdickson47537 ай бұрын
I know you're the two minute papers guy, but would you ever consider doing an overview video on the current best/workhorse simulation methods? There's so many, running on such similar looking benchmark tasks, that I feel lost every time a new one comes out. I just want to know what's out there, haha.
@cbuchner17 ай бұрын
the hydraulic press channel would love to work with these squishies
@AEFox7 ай бұрын
Amazing the new speed, I think it's important whenever you talk about speed (seconds per frame, for example), to post the specifications of the hardware used to achieve those results mentioned in the paper, so I've checked and it is: AMD Ryzen 5950X CPU, 64GB DDR3 RAM, and an NVIDIA RTX 4090 GPU.
@shahinsmith33497 ай бұрын
genius papper wowww loved it just imagine what could be possible in two more papper
@Chef_PC7 ай бұрын
It's nice to see TMP get back to roots. AI is amazing but this is the good stuff we've been missing.
@athok987 ай бұрын
"University of Utah & Roblox, USA" - why roblox? haha in 7:18
@arnoldbuskftw7 ай бұрын
Probably also works at Roblox
@leendert20297 ай бұрын
Learned more about programming from Roblox than the Uni.
@Alexey_Pe7 ай бұрын
It turns out (suddenly) the Roblox engine does not write itself
@cvspvr6 ай бұрын
roblox is interested in world domination
@SP-ny1fk7 ай бұрын
Is it calculating with air pressure? All the elastic bodies in the glass jar would cause suction, changing the dynamics. (No, going by the unchanged falling forms before hitting other objects) Is this the mother of all oversights?
@David_Stevens7 ай бұрын
Keep the videos coming! Thank you!
@MustacheMerlin7 ай бұрын
Now that's what I'm talking about!! Restir and cutting edge physics simulation videos one right after the other, and it's all hand crafted with no AI! This is what I am here for!
@cbuchner17 ай бұрын
Could this also simulate more rigid structures correctly? Then it could work for large scale simulations e.g. of earthquake scenarios. Shake up the whole city.
@sky1737 ай бұрын
Speed and 'how fast' it is seems to be mentioned all the time... on what computer? A super computer and/or a gaming computer?
@IAmGeeeWiz7 ай бұрын
If it is a supercomputer, these advancements are going to help us develop the same level of processing power on more accessible devices. When we look back 20 years to what a household computer could do and compare it to the standard computer today, the advancements have been huge. The speed of advancement is only growing so I'd guess that within 5 years, devices with the computing power to complete the simulations seen in the video today will be well within the public's reach, likely on devices such as or as small as our cellphones. This is however, just my assumptions.
@younesskafia41897 ай бұрын
Dr. Cem Yuksel continues to be part on amazing research projects lol. Props to the team for doing this job!
@tkzsfen7 ай бұрын
As a regular user of FEA and CFD, this is astonishing! Can't wait to see the jump in productivity in the coming years. This is what AI should be used for.
@sh5l3457 ай бұрын
How to use this in blender or unreal engine or whatever ?? Like what the skills I need to learn to be able to transfer research papers to real applications ??
@timojolivet7 ай бұрын
Hah I was watching distractedly, I though to myself "well OK there are some things where AI people are really useful" and then you said "no AI is used here". What a time to be alive!
@MrPicklock7 ай бұрын
How does this behave against explicit dynamic FE-simulations ? Is it „just“ creating nice pictures or is this actually generating realistic numbers ?
@JoshKings-tr2vc7 ай бұрын
This is absolutely amazing. A nice break from the AI stuff to talk about an amazing paper like this.
@jacejunk7 ай бұрын
Cool. I knew one of the authors, Cem, from grad school. Small world. Thanks for reporting, Károly. Connections like these emphasize the "human" in human ingenuity.
@marcelinomoreno45067 ай бұрын
You theorized a working set of physical laws as a thesis? Impressive!
@TheNemoff7 ай бұрын
Has a Houdini vellum enthusiast myself, I love this video
@Bloodlinedev7 ай бұрын
Ok, this looks like it can actually be used in games now. Not in a specialized, either optional or highly focused way but just as a general gameplay feature. So cool! (Ok, I didnt watch the whole video; seconds per frame obviously requires 2 more papers for usability in videogames :D)
@johanavril16917 ай бұрын
Wait if all nodes are independent of each other could this run on a gpu ?
@AdamMi17 ай бұрын
It's great to hear again about simulations and not just AI.
@Kknewkles7 ай бұрын
The occasional graphics/simulations video, eh? :^) Glad to have you back, if only for 8 minutes every once in half a year.
@publicspeaker40097 ай бұрын
4:22 well… this gives me a n idea for a video I can’t post on KZbin…
@woppats7 ай бұрын
Finally some old school 2 minute papers content!
@jeffg46867 ай бұрын
Imagine showing this to someone from the 90s or early 2000s, and saying, this is what's coming up, but you don't won't get it for 30 years.
@DownwithEA17 ай бұрын
Wow! Hats off to the researchers.
@coolbuddy95able7 ай бұрын
It is truly refreshing to hear "No AI was used here"
7 ай бұрын
Hardware kind of matters when talking about frames per second. Did I miss it? 3.6s/frame on consumer PC? Supercomputer?
@ankachen74687 ай бұрын
A high end consumer PC with RTX 4090 and Ryzen 5950
@tonythereader7 ай бұрын
I wonder if you wouldn't mind giving us some real practical applications where these are currently used or if they aren't used yet then where EXACTLY they could most likely be to be used? For each video.
@el-_-grando-_-_-scabandri7 ай бұрын
two weeks in CORN-flix
@tirushone64467 ай бұрын
when he said "HOLY MOTHER OF PAPERS!" I felt that
@AjSmit17 ай бұрын
don't get me wrong, generative AI is cool and all but i definitely missed me some Classic TMP
@Zizos7 ай бұрын
Do they sell tose algorythms to 3d software companies? Are they open source? Any idea?
@UnbipentiumM7 ай бұрын
I love it when you cover papers like this
@bzikarius7 ай бұрын
Amazing quality and speed! Stunning!
@shawnweil77197 ай бұрын
This is awesome I've been pretty down and sick lately but this made it a bit better 🙂
@victorfsaaa7 ай бұрын
Why the little cube was tossed away? In real world I understand but in a simulation, with perfect positioning, shouldn't be the lack of a lateral vector? Or it was some little wave in the bigger cube that pushed a little and it took it the perfect positioning?
@lukeewing42747 ай бұрын
I would guess some parm in the sim included noise, or there is a little noise inherent to the technique.
@alexc81147 ай бұрын
Yay, back to squishy satisfying physics papers 😌 I've been avoiding GenAI papers, but thats meant not watching Dr Károly
@joseperez-ig5yu7 ай бұрын
Hey Karoly, how fun it must be to go to work each day just to do simulations of this caliber!🎉😅😊
@abdelhakkhalil76847 ай бұрын
As a 3D hobbyist, at last we arrived there! I spent days simulating fluids, softbody and hardbody simulations that took several hours to simulate a few seconds. Will it come to our favorite 3D packages soon?
@TheGameGuruTv7 ай бұрын
nice seing some physics simulation again, always a highlight for me
@andydataguy7 ай бұрын
HOLY MOTHER OF PAPERS
@AllisterVinris7 ай бұрын
Now to do the the same but with tearing on top of elasticity (in the same simulation I mean). Next paper perhaps?
@jupitersky7 ай бұрын
Wonderful, I love really squishy balls!
@JNJNRobin13377 ай бұрын
any estimates for when this can be implemented into games without too much difficulty?
@vladthemagnificent90527 ай бұрын
thank you for the video. Always excited for ingeneous hand-crafted techniques!
@leendert20297 ай бұрын
0:29 Imagine, an airport with one million people bumping into each other!🤣🤣 4:56 Now, imagine, that all of these people are packed into a tiny teapot!
@the_curious17 ай бұрын
This looks promising 🤔 gotta apply that to some specific body parts for more stability. I love science ❤
@AdianAntilles7 ай бұрын
That is the first step to functional virtual muscles, right?
@zueszues97157 ай бұрын
What a time to bounced for alive !
@telebijeon31097 ай бұрын
The smell of those spiky ball toys would have been unimaginably bad irl.
@mahaddev7 ай бұрын
I'm sure the Corn industry is going to put a lot of money into these simulations.
@eSKAone-7 ай бұрын
Damn this first one looks incredible. Soon they can simulate everything.
@Maouww7 ай бұрын
This is amazing - no AI and we're at just a few seconds? That probably means we can do this in real time with AI.
@theencore3987 ай бұрын
I grabbed my papers so hard with this one that they managed bounced back somehow
@MarkHennessyBarrett7 ай бұрын
Dr. Papers, this was *thrilling!* (That's as best I can translate my last seven minutes of swearing and inchoate gibbering).
@SENYSENofficial7 ай бұрын
1:49 This could be very useful 😂
@Baekstrom7 ай бұрын
Game developers jumping on this paper in 3, 2, 1...
@AdamG17 ай бұрын
It's pretty amazing they can do this but KZbin video compression algorithm gets pixelated when showing so many different things moving around on the screen.
@leanshiza7 ай бұрын
Damn it was crazy when he showed the semi logarithmic scale
@mrburns3666 ай бұрын
I've spent most of my life researching things that jiggle. 😁
@josiahgil7 ай бұрын
I wonder how long it will take to get these technologies implemented into blender
@smorty35737 ай бұрын
No way, actual computer graphics? I was worried this would become one of these boring AI-only channels...
@TwoMinutePapers7 ай бұрын
I would absolutely love to do more of these, but I noticed that fewer and fewer of you Fellow Scholars are interested, so it might not be sustainable unfortunately - I still haven't figured out what to do about it!
@Sekir807 ай бұрын
@@TwoMinutePapers Pity. I love these kind of papers very much! AI is very popular everywhere if you not make videos about these papers they will fade int obscurity eventually. Remember: you have shown numerous with there original viewcount in a double or even in a single digit, claiming, if you not look at them and tell here nobody will know. It's a conundrum, I know. Sharing interesting news vs current buzz (ie money). De én bízom Önben, Doktor Károly! ;)
@Wobbothe3rd7 ай бұрын
Theres nothing boring about AI.
@flockenlp17 ай бұрын
Yes this is probably very usefull, but I need to know where I can get 2 hours worth of these mesmerising simulations in 4k and some popcorn!
@senkl_6 ай бұрын
seconds per frame when gaming: 👎 seconds per frame when simulating: 👍
@ewerybody7 ай бұрын
OOOOhhh SO nice 👌to see some non-ai papers here again!! Thank you :)
@andydataguy7 ай бұрын
Right!! Hope he does more on occasion. Especially in the graphics space or other practical applications
@stewiegriffin97687 ай бұрын
Balls teehee
@teddy36577 ай бұрын
Kinda glossed over it but the tear sim is super impressive
@maxwelikow91197 ай бұрын
Loving it but you forgot to explain the magic sauce how they made it
@wacka.7 ай бұрын
nice! where is the 88-line code version? ;D
@zaj0077 ай бұрын
Woo simulation content
@Martysama117 ай бұрын
This is insane.
@dxnxz537 ай бұрын
i love this channel
@ChuckSploder7 ай бұрын
FINALLY, NOT AN AI PAPER
@pranjal98307 ай бұрын
I was thinking we can make it a fully ai paper dedicated paper channel. It's not like that I don't like these types of videos.It just that people are less interested in other topics that people have no knowledge , I don't know it would be right or not but if there could be separate channels for only ai paper it will like the all fellow scholar very much.:)
@indianvfxschool7 ай бұрын
I have no idea where do all these crazy technology go? Why dont they make to solvers inside programs mostly. All the solvers are still very outdated.
@WirIez7 ай бұрын
Wow this is amazing
@asandax67 ай бұрын
R34 3D artists are drooling right now.
@om1gee7 ай бұрын
I feel bad for all armadillos watching this video without a trigger warning up front. Sorry guys. No actual armadillos were hurt in this research!
@ak-gi3eu7 ай бұрын
Airpot 1 mill bodies bump into each other💀
@BoghNorh2557 ай бұрын
it's only me or the wave effect feels unrealistic? does it would happen on a real life experiment?
@kaharagin7 ай бұрын
Trying to fix the chair while you sitting on it :D
@luc82547 ай бұрын
This combined with VR is going to be crazy immersive
@EqualToBen7 ай бұрын
Lol cool video, though for me imagining 50 million san franciscans crammed into a tea pot was not helpful in the slightest
@Queracus7 ай бұрын
i remember we ised to play with balls like this :D taking one string and spinnig the ball hahaha