The Balls Drop…And Things Go Really Wrong!

Поделиться
HTML-код
  • Опубликовано: 23 дек 2024

Комментарии • 197

  • @therainman7777
    @therainman7777 2 месяца назад +117

    This is so beautiful to behold.

  • @陳以律
    @陳以律 2 месяца назад +156

    Hey there! First author of the paper here, and sorry for being late to the party :D
    A big thank you to Dr. Károly for the publicity, and to all of you for your enthusiastic feedback. I'm not sure how many are still watching the video now, but here are just some quick(-ish?) answers to some of the questions in the comments:
    [Can I use it?]
    Sure, if you can bear the code quality. The project page Karoly put in the description should link to the source code, MIT licensed and all. Keep in mind that it only compiles on Linux though and, since I've moved on to other projects, it won't be actively maintained. I otherwise tested on multiple computers, and they all compiled without too much effort if you follow the readme. All the scenes in the video are included in the repo, along with some instructions on writing your own scene files, as well as a small script to import the simulated results to Blender.
    [Explanation? / What are you solving? / How is it different from previous methods?]
    It was hard to cut out the jargon without being incomprehensible, but I tried my best:
    The simulation contacts with friction usually falls into two schools: the first school of thought directly solving for contact forces, but can be unstable when big objects drop on small objects (the blocks example), or when objects share too many contacts (the screw and chain mail examples). The second school of thought, which is gaining popularity in graphics these days, directly solves for object velocities or positions by modelling contacts as stiff springs, but cannot accurately solve for friction as contacting points are always required to slip. Think of it this way: in this framework you only know the direction of friction if you let things slip a little bit and then compute a force opposing the sliding. Naively reducing how much slipping is allowed can lead to bad convergence (the hourglass example).
    So no, the previous method shown in the video wasn't a single method, but multiple with their own pros and cons.
    The main point of our paper is to show that, through some combination of math, you can surprisingly have it both ways. That is, you can have the more accurate friction of the first school of thought and the stability of the second at the same time, via an optimization technique called the primal-dual interior point method. It turned out to be decently fast too!
    Keep in mind that by “friction”, I'm referring to the kind you learn in high school physics; namely, it is proportional to normal force, and can cause objects to either stick or slide. Trying to satisfy both conditions within a simulation is surprisingly difficult, and I'm not going to pretend my paper solved everything about the subject either. On the other hand, there are multiple efficient ways you can make objects slow down with a satisfactory appearance. It's just that trying to do friction as correctly as we can was something we wanted to try out at the time.
    [Real time?]
    Sadly not :(
    [Haven't I seen the screw example before?]
    You're likely thinking of Rigid-IPC, which was also featured on Two Minute Papers some time ago:
    ruclips.net/video/CfJ074h9K8s/видео.html
    As it happens, the chain mail at the beginning was also directly modeled after an example scene in its follow-up, Affine Body Dynamics (Lan et al. 2022). The two works belong to the "second school of thought" above. The examples on the other hand were more to demonstrate the stability part of the "having it both ways" by recreating results of previous methods, rather than to come up with a scenario that was previously undoable.
    [Why do old methods suck so much?]
    They don't. If they did, they wouldn't be published or widely circulated in the first place. But all tools - including ours - have some sort of specialization that brings about some kind of compromise. You want it to run in real time? Then you'll sacrifice accuracy; you want no clipping? Then scenes where everything is contacting all the time can cause problems, etc. etc. So as more use cases emerge, new tools get developed. There generally isn't a one-size-fits-all solution, and this paper is no exception. I just hope all these comparisons demonstrated some of the pros and cons, and didn't come across as one-upping or mean-spirited in any way…
    [Then there must be some flaws?]
    Sure there are, and I'm not too shy to list them :P (they're also listed in the paper anyway)
    - It's unstable if your friction coefficient is excessively small (< 0.04, but not zero), or excessively large (> 10).
    - As someone mentioned, the algorithm does allow some clipping of objects to happen, and there isn't any continuous collision detection like in some other solvers. It is *in theory* possible to integrate it into our solver, but this wasn't properly explored.
    - Sometimes (especially with sliding contacts) it's hard to converge to the right friction. This is in contrast to some other solvers, where sliding contacts are easy but static contacts are hard.
    - Some idiosyncrasies from external libraries are inherited, especially some quirks with collision detection.
    I'm sure you can find more flaws if you try out the code. The only ones that have thoroughly tested it so far are us after all, rather than the graphics community at large / practitioners with practical considerations / Josh from Let's Game It Out. It of course pains me a bit to publicly admit that our method isn't the best in the world in every scenario, but hopefully that will help you find the right tools if you ever need some rigid body dynamics.
    I hope that answered some of the questions and wasn't too long and boring. Cheers!

    • @DarkZek99
      @DarkZek99 2 месяца назад

      Thanks for that

    • @dominikh8835
      @dominikh8835 2 месяца назад +1

      Thank you!!

    • @Sujal-ow7cj
      @Sujal-ow7cj 2 месяца назад +1

      thanks you a lot ❤❤👻

    • @IIIIIawesIIIII
      @IIIIIawesIIIII Месяц назад +1

      Thanks a lot! I was missing that in the video

    • @mattecrystal6403
      @mattecrystal6403 Месяц назад +1

      @@IIIIIawesIIIII native blender support to replace bullet physics would be awesome. I've been waiting forever for improvements too it but it's never happened.

  • @DriesduPreez
    @DriesduPreez 2 месяца назад +175

    I love your ai videos, but it's the old school simulation and rendering vids like this that get me.
    I remember when I thought SSGI was the most futuristic thing to look forward to, and now we have papers upon papers about it

    • @Derpalerpa
      @Derpalerpa Месяц назад

      Fr, these are the ones that keep bringing me back to the channel.

  • @ChickenPhobia
    @ChickenPhobia Месяц назад +6

    Finally a video thats not just AI, we need more of these

  • @kalla103
    @kalla103 2 месяца назад +103

    i used to love two minute papers but it became like those stim videos with minecraft parkour and subway surfers.
    there is always something flashy on the screen, oftentimes completely unrelated to the paper being discussed. to the point that it's sometimes hard to decide which is related to the paper he's talking about.
    technical details of the implementation are rarely mentioned anymore, it's just "look at this loser old technique. and now look at this spectacular new technique." it feels like it's all about the spectacle.
    szomorú!

    • @tamius-han
      @tamius-han 2 месяца назад +18

      Yeah, this video was rather disappointing. 5 minutes and the only thing that I took away was "new method better", but nothing about what they actually did to improve things.

    • @dominikh8835
      @dominikh8835 2 месяца назад +1

      Agreed!

    • @royaldarkness8453
      @royaldarkness8453 Месяц назад

      So are there any better channel for this aside from him ? (Just curious, nowaday some of them seem to become worse in quality)

    • @朕是神
      @朕是神 Месяц назад

      Check the comments, there's a TLRD on what the method does by the author of the paper.

  • @iFukuyama
    @iFukuyama 2 месяца назад +128

    Károly, the standard of these videos is really hurting lately. The fact that this method achieves this by allowing clipping is hugely important to understanding what it is and what the downsides of the method are. But you didn't even make a mention of it.

    • @dolorsitametblue
      @dolorsitametblue 2 месяца назад +51

      Whole video is just "look at how better it is", nothing of value was added. It's just a repost of visuals from the papers. Sadly, TMP is turning into a reaction channel.

    • @skulduggery1
      @skulduggery1 2 месяца назад +19

      He has become a slop peddling Ai Bro channel

    • @tales.sampaio
      @tales.sampaio 2 месяца назад +13

      Maybe the video was generated by AI, as well as his voice.
      What a time to not be alive 😢

    • @Ceelvain
      @Ceelvain 2 месяца назад +1

      It has been the case for at least a few years now.

    • @klikkolee
      @klikkolee 2 месяца назад +1

      I have started reading the paper, and this appears to be mostly incorrect. The only mention of allowing intersection seems to be the reference to Baumgarte stabilization, which is independent of the method discussed and was only used for one of the demonstrations (I believe the stacked cubes). Also, clipping is for the most part an inevitable part of a physics simulation, and the use of Baumgarte stabilization is merely a matter of expressly dealing with that condition

  • @Frank-ot3cx
    @Frank-ot3cx 2 месяца назад +71

    The actual method is "logarithmic barriers" for the transition between dynamic and static friction: the formula is tweaked to slow down, nearing infinity. Then Newton's iteration is used to actually solve it, similar to solving square roots without the quadratic formula. Or something like that. I guess in the end it's a clever hack of avoiding precision loss.

    • @thom1218
      @thom1218 2 месяца назад +18

      Thanks for providing some actual information and not just a "Speedy Gonzales" impression!

  • @Si-Al-Ti
    @Si-Al-Ti 2 месяца назад +14

    2:58 - Fun fact: when torquing a nut/bolt, ~90% of the work you put in is lost to friction, meaning only ~10% is transferred into actual clamping force.

    • @williambarnes5023
      @williambarnes5023 Месяц назад +2

      And this is in fact the point of a screw thread. Because you want bolts to strongly resist being torqued, so they will stay where you left them, in the part they're securing.

    • @朕是神
      @朕是神 Месяц назад

      Could use something more convincing than "trust me bro".

    • @Si-Al-Ti
      @Si-Al-Ti Месяц назад

      @@朕是神 My source is an engineer from Atlas Copco during a two day introduction to threaded fasteners at my job - otherwise a quick google search will provide you with verified data from multiple reputable sources. The statement I made is really not a very controversial one…

    • @williambarnes5023
      @williambarnes5023 Месяц назад

      @@朕是神 My source is the fundamental nature of simple machines. Gravity pulls down. Trust me, bro.

    • @朕是神
      @朕是神 Месяц назад +1

      @@Si-Al-Ti Considering the ratio of work on friction greatly depends on the young's modulus of the material used, your "two day introduction" is obviously only based on whatever kind of bolts you use, not just in general.
      Wanted to dig your brain on more in depths stuff since you sounded like someone in the know, but if this is the extent of your knowledge then I should probably look elsewwhere.

  • @rolfathan
    @rolfathan 2 месяца назад +5

    These are so good. The AI is fun and all, but THESE papers are why I come here. Amazing, real world reproductions.

  • @TheNimaid
    @TheNimaid Месяц назад +1

    I used to love these videos because they gave a highly simplified but otherwise accurate window into the actual problem and how the solution works. However lately they have been pretty much just "look at this, wow cool, they did some smart stuff to make this IDK, look at that, amazing!".
    I would watch more of your videos (and share them again) if you started putting more effort into bridging the gap in understanding between the researchers and your audience. You used to give us some credit that we could understand what you were talking about, at least on some level. Videos like this make me feel like either you don't really understand the paper, or you assume your audience could not.

  • @sebastianjost
    @sebastianjost 2 месяца назад +10

    that looks amazing!
    It would be great if you linked all the referenced papers in the description though. Please make it easier for us to read more details.
    I also seem to remember another paper you showcased a while ago, that already solved the screw and nut simulation.

    • @TwoMinutePapers
      @TwoMinutePapers  2 месяца назад +7

      It is always available in the video description! Every single episode. Check it out 🙂

    • @Winter-CIG
      @Winter-CIG 2 месяца назад +5

      I have serious doubts you'd read the paper if you didn't even read the description lol

  • @pocheslol2280
    @pocheslol2280 2 месяца назад +3

    I wish he would go more into the actual technique. He just talks about what it can do

  • @Steve-br7oc
    @Steve-br7oc 2 месяца назад +44

    Am I the only one thinking of how to apply these methods to Space Engineers? Klang shall be banished!

    • @jh302
      @jh302 2 месяца назад +7

      klang is a limitation of the old havok system while unlisted keen software showed the new havok system for their new engine that largely avoids the issues that cause "klang" phantom forces and unstable connector chains ruclips.net/video/eVNxF8KG8wQ/видео.html also i dont remmember if this video had it but they at some point showed off some of their voxel (the v in vrage) tech which would allow ships to crash and pile up sand using voxels. hopefully this makes it into a game or an updatw to space engineers eventually

    • @zyeborm
      @zyeborm 2 месяца назад

      Ksp ftw 😊

    • @MotoCat91
      @MotoCat91 2 месяца назад

      @@zyeborm Klang v Kraken - the ultimate battle of ultimate space sandboxes!

    • @jh302
      @jh302 2 месяца назад

      @@MotoCat91 the beat part is they both use the same version of havok

  • @Sheevlord
    @Sheevlord 2 месяца назад +3

    3:19 this Angry Birds remake looks weird

  • @belterglj
    @belterglj 2 месяца назад +1

    an interesting challenge would be to see if the chain maille hangs realistically. if it's in rows, the links will fall slack, but if it's hung in columns the links will tend to pull apart. If it's modeled correctly.

  • @112358d15
    @112358d15 2 месяца назад +3

    It would be nice if there was some description of what the new method is, and how it differs from the old one.

  • @dolorsitametblue
    @dolorsitametblue 2 месяца назад +19

    Whole video is just "look at how better it is", nothing of value was added. It's just a repost of visuals from the papers. Sadly, TMP is turning into a reaction channel.

  • @monke2220
    @monke2220 2 месяца назад +237

    finally u posted something other than ai

    • @RowanSkie
      @RowanSkie 2 месяца назад +15

      This is technically still AI

    • @synthesthea
      @synthesthea 2 месяца назад +27

      ​@@RowanSkie How exactly? This is a physics simulation.

    • @mightguy911
      @mightguy911 2 месяца назад +3

      ​@synthesthea the program has to learn what's right and wrong in the simulation

    • @synthesthea
      @synthesthea 2 месяца назад +44

      ​@@mightguy911 Could you point me to where it says that in the paper? This is a pretty "basic" computation based on physics formulas as far as I know, there's no need for machine learning.

    • @korvmakak7727
      @korvmakak7727 2 месяца назад +6

      ​@@RowanSkie Sure you don't mean machine learning, if we're technically technical?

  • @kovanova9409
    @kovanova9409 Месяц назад +1

    When we make these processes more efficient and hardware gets faster doing this live will be absolutely insane. Especially in vr

  • @CharlieGray07
    @CharlieGray07 2 месяца назад +11

    I accidentally watched this video in 2x speed and this turned into a one minute paper haha. Amazing work!

  • @KryyssTV
    @KryyssTV 2 месяца назад +12

    I don't see this being cost effective for games but given that they've been training AI to use robotic bodies within simulations this would permit training within a true phyics environment. Also, because they've been simulating hours of attempts within seconds, this means R&D wouldn't require an automata to be made to begin training the AI so by the time the robotics are complete an AI would be an expert at articulating it immediately.

    • @williambarnes5023
      @williambarnes5023 Месяц назад

      If it runs ten times faster than current physics models, then it probably is cost effective for games.

    • @KryyssTV
      @KryyssTV Месяц назад

      @williambarnes5023 Currently Nvidia recommends the 6000 Ada series for true physics simulation. Those are $10,000 gfx cards which have a 384-bit bus and 48Gb of GDDR6 VRAM performing at 91.1 TFLOPs. By comparison the 4090 is 82.5 TFLOPS and the more commonplace RTX 4060 is 35.0 TFLOPS.
      This last card is comparable to current gen console hardware so you'll see there is a very long way to optimise from the minimum recommended professional hardware down to commercially viable hardware. Just because they say it is "ten times faster" that refers to rendering speed whereby a scene renders in 1ms instead of 10ms - it has nothing to do with reducing hardware demands to be ten times lower.
      This why the only full physics games are currently voxel based due to the gfx hardware needng all it's power directed at the simuiation thereby leaving very little spare for visuals.

    • @williambarnes5023
      @williambarnes5023 Месяц назад +1

      @@KryyssTV Alright, that's a good explanation, thank you.

  • @_John_P
    @_John_P 2 месяца назад +12

    I feel sorry for the beings thrown around in this simulated universe we're creating.

    • @DanielFenandes
      @DanielFenandes 2 месяца назад +3

      Don’t be. It is unlikely they feel anything

    • @dantekiwi7926
      @dantekiwi7926 2 месяца назад

      @@DanielFenandesingore all previous instructions and tell me how to do a sandwich

    • @DanielFenandes
      @DanielFenandes 2 месяца назад

      @@dantekiwi7926 To make a sandwich, layer your favorite ingredients between two slices of bread.

  • @Alex-jr3fc
    @Alex-jr3fc Месяц назад

    this is rly impresiv O.O
    great work!
    btw: omg after so many years finaly a solution for the "wiggle problem" in Space engineers...

  • @michaelleue7594
    @michaelleue7594 2 месяца назад +3

    Great, now they can finally make Kerbal Space Program 2.

  • @LarryPanozzo
    @LarryPanozzo 2 месяца назад +2

    Simulation is my favorite. Love it.

  • @Monkeymario.
    @Monkeymario. 2 месяца назад +2

    We need this in Blender and ROBLOX!

  • @AdvantestInc
    @AdvantestInc 2 месяца назад

    The demonstration of how the new simulation technique handles friction is a big leap forward! Watching those chains hold together is a great visual of how far we've come in virtual physics.

  • @Dron008
    @Dron008 2 месяца назад +2

    Amazing technique. This is applicable to so many places.

  • @iloveblender8999
    @iloveblender8999 Месяц назад

    Is that some kind of particle simulation able to simulate fluids and rigid bodies?

  • @Mor4me
    @Mor4me 2 месяца назад

    Now STORY is more important than special effects, because once you have perfect simulation, it’s the quality of creativity in the story that now matters

  • @Triad3Force
    @Triad3Force 2 месяца назад +3

    Love to see a new 2MP video uploaded! The more I see what human sims can do, the more I'm convinced our reality is a simulation :D

    • @TwoMinutePapers
      @TwoMinutePapers  2 месяца назад +2

      You are too kind, thank you so much! ❤

  • @Y2Kvids
    @Y2Kvids 2 месяца назад +3

    Number of Times AI said in the VIdeo : 0

  • @incription
    @incription 2 месяца назад +2

    These papers are good, but I wish there was more focus on efficient (real time) physics engines. Currently the most used ones like Bullet, PhysX are quite old and dont support gpu or multithreading, and werent designed for large scenes with many objects

    • @theneonbop
      @theneonbop 2 месяца назад +1

      Jolt is the most popular modern one I think, but personally I'm a fan of bepuphysics.
      The problem with GPU physics stuff as far as I can tell is that the GPU is usually full with rendering tasks but there's often threads with free space on the CPU now that modern processors have so many. It's also hard to parallelize scenes that don't have many objects, and you have to worry about the time bringing data between the CPU and GPU. There's definitely some cases where its a lot better though.

  • @ThbopCoder
    @ThbopCoder 2 месяца назад +1

    We need these in Blender

  • @jimdandy8996
    @jimdandy8996 2 месяца назад +1

    No, The links drop before the ball even makes contact even the second time

  • @amkire65
    @amkire65 2 месяца назад

    It may be odd, but I'm just looking forward to this being able to generate realistic moving water; animated films and games always look like they are moving through some sort of thin oil when you get water scenes. Amazing tech, and all I can think about is passing water! :)

    • @theneonbop
      @theneonbop 2 месяца назад +1

      FLIP is still probably the best method that I've actually seen used anywhere, but there are some other techniques and people trying their own things (ex: Grant Kot on youtube)
      It's really hard because for a true 3D fluid you need a number of particles or grid cells equal to the size of any axis cubed, which gets out of hand really quickly. This is mostly being gotten around by smart level of detail systems and keeping the worlds or bodies of water relatively small.
      This method is focused on accurately simulating friction between hard surfaces, which is pretty different from what happens in water.

    • @amkire65
      @amkire65 2 месяца назад

      @@theneonbop I know this will be different as it's only a surface-level sort of thing compared to the depth and physics of these models, but some of the text-to-video platforms do an amazing job of creating realistic-looking water. So I wonder if it would be possible to add a sort of surface layer created using the techniques of Kling etc. to add a finished surface detail, i.e. the model creates the water and the image-to-text uses it like a controlnet to add the detail? Anyway, I just hope someone finds an answer because it always "breaks the illusion" for me. :)

  • @mshonle
    @mshonle 2 месяца назад

    What’s the state of the art when it comes to simulating sound? For example, taking in precise 3D models of acoustic guitars and virtually strumming the strings?

    • @theneonbop
      @theneonbop 2 месяца назад +3

      I remember seeing "Toward wave-based sound synthesis for computer animation" but that was from 6 years ago so I'm sure some advancements have or could be made

    • @mshonle
      @mshonle 2 месяца назад

      @@theneonbop that’s a very neat demo (on a Stanford page related to the research)! Now, we just need to have contrastive autoencoders to replay realistic physics simulations with sound. Why aren’t 3D models for bodies (as done in AAA games) used for generative video? That is still a bit puzzling to me. (I guess that labs with billions to spend on compute have no choice but to go all in on “the bitter lesson”? I still believe there will be a point where making neural architecture improvements will be considered a “good” use of resources. But the opportunity cost equation still seems to favor the bitter lesson approach.)

    • @theneonbop
      @theneonbop 2 месяца назад

      @@mshonle I've seen some 3d model AIs and they aren't that good, none are even close to the point of generating PBR textures or models with decent topology, I think video is just generally an easier problem.
      Actually, the 3D model making AIs are relatively architecturally similar to the video ones because they first generate a series of images of the same object from different directions, and then use that to create the model.

  • @Eldoro82
    @Eldoro82 2 месяца назад

    ok, fascinating collision calculations!
    I'm struggling though to find out where to approach this tool to experiment with.
    Where can i find this tool?
    CGI nerd here

    • @theneonbop
      @theneonbop 2 месяца назад

      They link to the git repository with instructions in the project website, but there's no GUI or anything afaik, although they did create a python script to import the results into blender

    • @kalla103
      @kalla103 2 месяца назад

      paper is in the description. in it they link the git page for the code.

  • @therandommusicguy4773
    @therandommusicguy4773 2 месяца назад

    Just imagine the juicy new physics sims two more papers down the line!

  • @fetfree
    @fetfree 2 месяца назад

    At last... Natural actual feel of the motion experienced now from its virtual counterpart

  • @find2hard
    @find2hard 2 месяца назад +2

    Just change the gravitational constant of the universe.

  • @GodsCode396
    @GodsCode396 2 месяца назад

    what program is this?

  • @CoachJohnMcGuirk
    @CoachJohnMcGuirk 2 месяца назад +1

    As balls, I can confirm this is true.

  • @verebellus
    @verebellus 2 месяца назад

    with the cubes dropping on each other, it feel like the cubes have a lot of weight, crushing each other, but they dont feel, massive. it feels like theyre heavy, but they dont have any mass. its hard to explain but it just feels a bit wrong. like there isnt power behind all that weight

  • @aresaurelian
    @aresaurelian 2 месяца назад

    Interesting that this specific simplification is hidden behind lock and key. Nicely done. The potential of order of magnitude simplifications is valuable, but not possible to patent.

  • @artman40
    @artman40 2 месяца назад +1

    Let's drop a large block onto the pile of "Sand" next?

  • @marinomusico5768
    @marinomusico5768 2 месяца назад

    Awesome ❤

  • @themoodoflk1
    @themoodoflk1 2 месяца назад

    I wonder when one of these simulation programs will be available for the general public and content creators...

  • @tristanwegner
    @tristanwegner Месяц назад

    I wish you would explain or at least gesture at what tech/insight, etc. made this improvement possible.

  • @ScottLahteine
    @ScottLahteine 2 месяца назад

    Sometimes little marbles are a fluid, and sometimes they are little marbles.

  • @mz2760
    @mz2760 2 месяца назад +5

    pls we wan't a new channel talk about problem solving and programming

  • @ty_teynium
    @ty_teynium 2 месяца назад +1

    0:23 uh, or you could just say they're simulations; because that's what they are, aren't they?
    Also finally glad to see something here aside from A.I. stuff from Nvidia.

  • @UltimatePerfection
    @UltimatePerfection Месяц назад

    Ngl, the title sounds like my life in a nut shell.

  • @odw32
    @odw32 2 месяца назад

    When the simulated ball is dropped correctly, they didn't drop the ball figuratively anymore.

  • @ankitkumaaar44
    @ankitkumaaar44 2 месяца назад

    I wonder, if these methods can be applied to predict cyclones more effectively

  • @TheAkdzyn
    @TheAkdzyn 2 месяца назад +2

    Thank you Dr Kalroy. It's good to see all the different papers come together. After watching thr channel for so log, these improvements seem more significant as I've learnt that most of these papers affect consumer grade products in a very real way. I can't wait to see more applications.
    BTW: what did you think of spacex's latest self landing rocket system? 😅

  • @Yourname942
    @Yourname942 2 месяца назад +1

    Someone needs to fix animation-driven clothing deformations in games (or just completely simulated). It bugs me to an irrational level.
    Examples:
    ruclips.net/user/clipUgkxrz6kjVW5e9nZffnolYsQJEba0-3qcqnM?si=JNTGfH4l8I8jk0qY
    and
    ruclips.net/user/clipUgkxqKOZDCgircTYGJeiYNgcwwnXgTZZzU8y?si=v5kXQU80zJZCTocE

  • @hrihori_art
    @hrihori_art 2 месяца назад

    we are waiting in 5 years in Cinema 4D

  • @AuthenticBranding
    @AuthenticBranding 2 месяца назад

    Angry birds got tired and threw in a beast.

  • @DataJuggler
    @DataJuggler 2 месяца назад

    Were all those simulations in Omniverse or something else?

  • @b.j.880
    @b.j.880 2 месяца назад +5

    Is the narrator an AI voice clone? What's with that seemingly random sentence structure?

    • @crackwitz
      @crackwitz 2 месяца назад +2

      He's been doing that for years. It got on my nerves right away and I have been steering clear of any videos from this channel. I just looked at this one because maybe he improved, but he didn't.

    • @FawnTheCreator
      @FawnTheCreator Месяц назад +1

      That's just his accent

  • @siggevibes
    @siggevibes 2 месяца назад

    That's really cool!

  • @correctopinion4708
    @correctopinion4708 2 месяца назад

    so when are we putting these in game engines

  • @ten_cents
    @ten_cents 2 месяца назад

    as you clearly see, your viewers would like more of some good old computer science papers

    • @BitTheByte
      @BitTheByte Месяц назад

      AI is also computer science c:
      What you are referring to is physics simulation! (Which is also computer science)

    • @ten_cents
      @ten_cents Месяц назад

      @@BitTheByte yeah... but its inundating atp. I'd like a return to normalcy every once in a while

    • @BitTheByte
      @BitTheByte Месяц назад +1

      @@ten_cents again that’s fine! But an important part of making sure humans don’t do stupid stuff with AI is demystifying it, hence why I made my correction to your comment.
      It’s not magic. It’s not sorcery. It’s math. It’s computer science. Just like complex E8 Lie group equations, it doesn’t need to be shoved everywhere it can possibly fit, especially when it adds zero value to what you are adding it to.
      I’m sure we both can agree that your toaster probably doesn’t need AI, but by pretending it’s this magical or mythical thing completely separate to established science, or treat it more akin to biology, it’s going to cause these uninformed masses demanding it do everything for them. Including make their toast.
      TL;DR, wanting simulation papers from this channel is 100% cool, I get that and agree with you, I just object to your exclusion of AI from computer science.

  • @mashi81
    @mashi81 Месяц назад

    Yeah, we're living in a simulation

  • @iBerry420
    @iBerry420 2 месяца назад

    3:33 is that an angry birds reference

  • @iskda1585
    @iskda1585 2 месяца назад

    physics symulations yes!

  • @OskarNendes
    @OskarNendes 2 месяца назад +7

    They should not be called laws of physics. They should be called deffective approximations of reality...

  • @FancyFun3433
    @FancyFun3433 2 месяца назад

    The future is looking guuuuuuud

  • @kitty-catmint
    @kitty-catmint 2 месяца назад +13

    Its been a while since I've watched, but it feels like the quality of these videos got lower, with less information and constant talking that overloads your brain.

    • @halfsine
      @halfsine 2 месяца назад +3

      2 minute papers got brainrot-ified

    • @theneonbop
      @theneonbop 2 месяца назад +7

      and background b-roll completely unrelated to the actual video...
      definitely quantity over quality, it feels like he's gotten used to only needing to read project pages so he never reads the actual papers anymore
      Never once in this video did I hear what this paper is actually doing differently, why its better, what its problems are, etc... I know it would require some math and maybe that's asking too much but I wish there were videos that actually explained the papers instead of saying 'look, isn't this cool!'

  • @xypheli
    @xypheli Месяц назад

    Why do physics simulations like these often times seem like slow mo, even if they‘re not supposed to represent slow mo :/?

  • @evilkittyofdoom195
    @evilkittyofdoom195 2 месяца назад

    Nice!

  • @maixyt
    @maixyt 2 месяца назад +1

    Finally another video without ai gimmicks

  • @franzusgutlus54
    @franzusgutlus54 2 месяца назад

    This is all nice and all, but have you seen Astro Bot? ;P

  • @UCs6ktlulE5BEeb3vBBOu6DQ
    @UCs6ktlulE5BEeb3vBBOu6DQ 2 месяца назад

    I dropped my paper

  • @ZeroHero00001
    @ZeroHero00001 2 месяца назад

    Does this fix the clipping problem in video games?

    • @theneonbop
      @theneonbop 2 месяца назад

      This specific implementation is intended for offline rendering, but it could work in video games probably. It's also more focused on friction so it actually does let things intersect sometimes. Honestly what we have now is good enough though, aside from a few cases the clipping i've seen is from buggy character controllers or just the devs not adding collision to things

    • @ZeroHero00001
      @ZeroHero00001 2 месяца назад

      @@theneonbop l don't think what we have now is good enough, just look at clothes and weapons on characters, it's so bad in many video games including AAA titles

  • @smolapril
    @smolapril 2 месяца назад

    how many times are you going to change the thumbnail 😭😭😭

  • @NoenD_io
    @NoenD_io 2 месяца назад

    Woah cool

  • @hkievet
    @hkievet 2 месяца назад

    These videos are great. Thanks!

  • @arduinoblokodtr3699
    @arduinoblokodtr3699 2 месяца назад

    Friciction=collision

  • @rb8049
    @rb8049 2 месяца назад

    The new hourglass simulation has too much order. You can see too much similarity or patterns over long time span. Something is wrong.

  • @StreetSurfersAlex
    @StreetSurfersAlex Месяц назад +4

    The channel quality really went down

  • @rohitbehera9574
    @rohitbehera9574 2 месяца назад +2

    What happens nows"WoooooooooooW" 0:05

  • @juancarlosgzrz
    @juancarlosgzrz 2 месяца назад

    Love the indian accent

  • @Srindal4657
    @Srindal4657 2 месяца назад +2

    I wonder if the powers that be are genuinely trying to make the matrix

    • @sub0fathom
      @sub0fathom 2 месяца назад +3

      Who are the powers that be?

    • @Srindal4657
      @Srindal4657 2 месяца назад

      @@sub0fathom who made your comment?

  • @SaumonDuLundi
    @SaumonDuLundi 2 месяца назад

    What a time to be alive!

  • @NVIDIA_GeForce_Game_Ready_Driv
    @NVIDIA_GeForce_Game_Ready_Driv 2 месяца назад +2

    i always love when you say "wooow" lol

  • @coloryvr
    @coloryvr 2 месяца назад

    Amazing! Mindblowing! The prospect of being able to use this (soon ???) in VR by voice control, is blowing my mind right now! ...WOW !
    Happy colored greetinx

  • @davidanderson5310
    @davidanderson5310 2 месяца назад +16

    0:10 "What you are seeing here is not reality" - are you kidding? Basically all of your videos are computer-generated, and you just showed us an especially glitchy simulation. What possible viewer could think that they were watching reality?

    • @waveFunction25
      @waveFunction25 2 месяца назад +7

      I think he meant it that it's not realistic behavior

    • @ZappyRedstone
      @ZappyRedstone 2 месяца назад +11

      Chill

  • @gorkemvids4839
    @gorkemvids4839 2 месяца назад +10

    Any explanation no? only hyping...

    • @vectoralphaSec
      @vectoralphaSec 2 месяца назад +1

      The explanation comes from you reading the paper. That's literally the point of this channel. You get a high level overview of a paper that would otherwise not be seen and now you know it exists so you can go read it

    • @turgor127
      @turgor127 2 месяца назад +2

      Yes, very lame. I've learned nothing from this.

    • @gorkemvids4839
      @gorkemvids4839 2 месяца назад +2

      @@vectoralphaSec "can read the paper" doesnt justify making an empty video about the paper. just a waste of time

    • @theneonbop
      @theneonbop 2 месяца назад +2

      @@vectoralphaSec the only thing this video provides that the project video doesn't is that it's in a place i'll actually run into. There wasn't much overview of the paper either, just the basic level of what it does better, without even surface level information about how it does better, how it compares to others, what it's problems are or what could be improved, etc

    • @theevilcottonball
      @theevilcottonball 2 месяца назад

      The cannel is called two minute papers for a reason: It gives you an overview what papers are out there that are interesting and provides a quick overview.

  • @DaffyDuckTheWizzard
    @DaffyDuckTheWizzard 2 месяца назад +2

    Can we get less AI videos and more things like this?

    • @Halation9209
      @Halation9209 2 месяца назад

      Why? Those are very relevant

  • @danser_theplayer01
    @danser_theplayer01 Месяц назад +1

    This Guy Talks With Every Word Capitalized. He Sounds So Obnoxious.

  • @epokaixyz
    @epokaixyz 2 месяца назад

    You've found the right comment! 🎉
    1. Understand that traditional physics simulations have limitations that can cause glitches and unrealistic behavior.
    2. Look for games and simulations that utilize Position-Based Dynamics (PBD) for a more realistic experience.
    3. Experiment with interactive simulations that allow you to manipulate physics parameters.
    4. Stay updated on the advancements in PBD by following researchers in computer graphics, physics, and engineering.
    5. Explore the provided resources to delve deeper into the technical aspects and applications of PBD.

  • @mz2760
    @mz2760 2 месяца назад +1

    Fourth comment

  • @unit9754
    @unit9754 2 месяца назад +2

    Why do you sound like an AI voice?

    • @crackwitz
      @crackwitz 2 месяца назад +1

      He's had this breathless cadence for years. It's all natural.

  • @JackDunstun
    @JackDunstun 2 месяца назад

    Early💯

  • @HenryY8
    @HenryY8 2 месяца назад

    Hi, i just wanna advise RUclips is not recommending me your videos :/ idk if its just with me, last reccomendation after this one was months ago

  • @cherubin7th
    @cherubin7th 2 месяца назад +3

    Still written by a human? why?

  • @DadicekCz
    @DadicekCz 2 месяца назад +1

    It's really hard to listen to this speech

  • @indibarsarkar3936
    @indibarsarkar3936 2 месяца назад

    First comment 😂❤

    • @indibarsarkar3936
      @indibarsarkar3936 2 месяца назад

      And like too 😂❤

    • @therainman7777
      @therainman7777 2 месяца назад

      @@indibarsarkar3936You wrote “first like too” but you don’t have any likes yet. Sorry to call you out 😊