3D Gaussian Splatting - Why Graphics Will Never Be The Same 

No nonsense. No filler. No BS. Just pure information. Cheers dude.

I've learned so much, but so little at the same time 😂

That "unlimited graphics" company Euclidean was working with tech like this at least a decade ago. I think the biggest pitfall with this tech right now is that none of it is really dynamic, we don't have player models or entities or animations. It's a dollhouse without the dolls. That's why this tech is usually used in architecture and surveying, not video games. I'm excited to see where this technique can go if we have people working to fix its shortcomings.

It could work really well for spatial film making, but for 3D interactive game-engine based applications, it might be an optimisation nightmare to real-time move a bush somewhere when it's made of 3 million gaussians.

this man can condense a 2 hour lecture into 2 minutes. subbed

this requires scene-specific training with precomputed ground truths, if this can be used independently for realtime rasterization that could be a big breakthrough in the history of computer graphics and light transport.

If this takes off and improves I could see it being used to create VR movies, where you can walk around the scene as it happens

Man this was so good, please do more stuff. This content scratches an itch in my brain I didn't know I had. So so good.

Concept is cool, but your editing is really great! Reminds me of Bill Wurtz :D

This technique is an evolution, one could say it's an evolution from Point Clouds. The thing that most analysis I've seen/read is missing is that the main reason this exists now is because we finally have GPUs that are fast enough to do this. It's not like they're the first people who looked at point clouds and thought "hey, why can't we fill the spaces *between* the points?" EDIT: I thought I watched to the end of the video, but I didn't, the author addressed this in the end :) It's not just VRAM though! It's rasterization + alpha blending performance EDIT2: you know what I realised after reading all the new things coming out about gaussian splatting. I think most likely this technique will first be used as background/skybox in a hybrid approach

Perfect video on an absolutely insane topic. I’d love more bite-sized summaries like this on graphics tech news!

i love how condensed and straight to the point this is

Would be great for something like Myst/Riven with premade areas and light levels. It doesn't sound like this method offers much for dynamic interactivity (which is my favourite thing in gaming). It would be great for VR movies/games with a fixed scene that you can look around in.

the highly technical rapid fire is just what i need. the editing and the graphic design is just great, keep it coming i love it!

Has to be the cleanest and most efficient way I got tech news on youtube. Keep it up my dude

I feel like I just took a shot of information, this is the espresso of informative content on RU-vid

Wow. Never seen someone fit so much information in such a short timeframe while keeping it accurate and especially easy to take in. Way to go!

This dude is the pinnacle and culmination of gen z losing their attention span

most compelling way to present, my recall is much higher from the way you make it so entertaining. Kudos!

this is the content i need in my life, no filler. thanks

I like the calm and paced approach to explaining the technique.

In the current implementation it reminds me of prerendered backgrounds. They looked great but their use was often limited to scenes that didn't require interaction like in Zelda: OOT or Final Fantasy VII.

Never thought id see the video version of an abstract before, very well done though. really does feel like ive just stepped into a researchers room right when they're about to finish up their 6 years of research and put it all together in one weekend without sleeping on 18 cups of extra caffeine coffee.

Please be the 2MinutesPaper we deserve (without fillers, making a weird voice on purpose and exaggerating the papers). Good stuff, really liked the video.

When people begin to do this on a larger scale, and with animated elements, perhaps video, ill pay attention. If they can train the trees to move and the grass to sway, that will be extremely impressive, the next step is reactivity which will blow my mind the most. I dont see it happening for a long time.

Very much a niche and limited method, that will become more practical and usable once it gets integrated into a more traditional rendering pipeline in a similar way that path tracing is still very much impractical for full scene rendering, but becomes a great tool if some scope limitations are applied and it gets used to augment the existing rendering model instead of replacing it.

You deserve every view and sub you got from this. Amazing editing, quick and to the point.

Jeesus it's been so long since Iv'e seen something so direct and un-bloated that i almost got whiplash. Cheers very much

Please continue to make videos like this that are engaging but also technical. From a software engineer and math enthusiast.

At the moment, photogrammetry seems a lot more applicable as the resulting output is a mesh that any engine can use (though optimization/retopology is always a concern) whereas using this in games seems like it requires a lot of fundamental rethinking but has the potential to achieve a higher level of realism.

Quick and informative and I love your editing style

video explanation is packed, couldn't even finish my 3d gaussian splatting on the toilet

the man who made a 7 min video worth of something to a 2 minute barrage of info - I like it

This looks a lot like en.wikipedia.org/wiki/Volume_rendering#Splatting from 1991, I wonder if there is any big difference apart the training part, also I know everybody said the same, but your editing is so cool. It's so dynamic, yet it manages to not be exhausting at all

Love your editing and humor!

You left out every useful detail. If a gaussian is just a blob sprite, how do you do lighting, shadow, reflection etc.

I absolutely love this style of informative video. Usually I have to have videos set to 1.5x because they just drag everything out. But not here! Love it.

This could be used for film reshoots if a set was destroyed, but in a video game the player and NPCs would still need to have some sort of lighting/shading.

I wish all information was formatted like this. My new favorite channel

Why did this lock my attention in so well? Keep up the great work!

It's more niche than photogrammetry because there's no 3D model to put into something else. But with a bit more work I'd love to see this be a feature on a smartphone.

Congrats on making like a solidly informationally dense video, we like this!

within a couple of years we could have photo-realistic video games, which is amazing

This is the first time I've seen an editing style similiar to Bill Wurtz that not only DIDN'T make me wanna gouge my eyes out, but also worked incredibly well and complimented the contents of the video. Nice!

This is the power thirst of super complex graphics algorithms, and I'm totally here for it.

I've never learned so much about a subject I never heard about before in such a short ammount of time. Incredible!

This is like if Vsauce and Bill Wurtz had a lovechild. Nice video!

This is the most concise explanation of gaussian splatting I have stumbled across so far. Subscription achieved.

I cannot overstate how much I appreciate this approach to delivering information concisely. Thank you sir.

I literally don't care about the subject, but the way you did this... possibly the greatest YT video of all time. 2 minutes flat. No nonsense. Somehow hilarious. Kudos!

I had to watch this with subtitles because I'm at a restaurant and it feels like I just came out of a washing machine

So fun to watch. I want all research papers explained this way, even the ones in less visual fields. Subscribed!

I wonder how we'll get dynamic content into the 'scene'. Will it be like Alone in the Dark where the env is one tech (for that game, it was 2D pre rendered) and characters are another (for them, 3d poly). Or if we will create some pipeline for injecting / merging these fields so you have pre-computed characters (like mortal combat's video of people). Could look janky. Also I don't see this working for environments that need to be modified or even react to dynamic light, but this is early days.

I didn't understand a single thing but I think you're passionate about it so I'm going to do the dad thing and fully support you.

Short form information blast. Just long enough to scratch my ADD parts, i love it

For now it’s niche. I imagine it could be used in games blended with traditional rendering pipelines. E.g. use this new method for certain areas that need a light level of detail.

welcome back to two minute papers. i’m your host, bill wurtz

Video topic aside, your style of delivering info is top notch mate!

Very good video i love how much info you packed in such a short amount of time

Your video is spot on! HTC Vive/The Lab were the reasons why I got into VR. I loved the photogrammetry environments so much that it's my hobby to capture scenes. Google Light Fields demos were a glimpse of the future, but blurry. These high quality NeRF breakthroughs are coming much earlier than I thought it would be. We will be able to capture and share memories, places... it's going to be awesome! I don't know if Apple Vision Pro can only do stereoscopic souvenirs capture or if it can do 6dof, but I hope it's the latter :,D

this could be done using images from hyperrealistic renders instead of irl photos too, right? to move around in a disney cgi level environment that wouldn't be possible in realtime normally

whoah this was fast, i think that if this dude makes a 2 hour essay video i may even learn real happiness

This is exactly what I wanted. Keep these videos up, subbing now!

Interesting!!! I always think back to when I was doing my degree in the 90s, and Ray Tracing was this high end thing PhD students did with super expensive Silicon Graphics servers, and it was always a still image of a very reflective metal sphere on a chess board with some kind of cones or polyhedra thrown in for kicks. It took days and weeks of render time. About 25 years passed between when I first heard of ray tracing and when I played a game with ray tracing in it. I might not be 70 when the first game using a Gaussian engine is released, but I wouldn’t imagine it happens before I’m 60. Still very interesting, though!!!

the issue is it does not have the 'logic' - so no dynamic light, no possibility to identify a gameobject directly like : 'hey do a transform of vector3 to the bush there' => no 'information' of such a bush. Let sees where it will bring us of course, but it looks more like a fancy way to represent a static scene. Probably it can be used in an FX for movie, where you can do something on a static scene, and you do something with 3D stuff inside this 'scene' I do not know ...

Subscribed: because you can condense quality information in 2 minutes, no bs, just to the point.

This was amazing. Thanks for the humorous take. Keep going!

I'd like to see more research done into this to see how to superimpose dynamic objects into a scene like this before it has any sort of practical use in video games but for VR and other sorts of things, this could have lots of potential if you want to have cinema-quality raytraced renders of a scene displayed in realtime. Doesn't have to be limited to real photos.

I was in college back when deferred shading was just being talked about as a viable technique for lighting complex scenes in real-time. I even did my dissertation on the technique. Back then GPU's didn't have even close to the memory needed to do it at a playable resolution, but now pretty much every game uses it. I can see the same thing happening with 3D Gaussian Splatting.

That was the best 2(ish) minutes of listening to someone describing a new thing I've ever spent in my life. Also, this would be amazing if it could be implimented into games/VR/AR.

I appreciate that the video took the minimum amount of time possible.

Great video, do you plan more like this? Terse, technical, about 3D graphics or AI. Basically, 2 minute papers, but with less fluff.

I don’t know much about rendering but this sounds so smart. You take a video, separate the frames, do the other steps, and now you have this video as a 3d environment

Beyond the Gaussian Splatting, great Audio Splatting with the QnA style format to answer all the "ya but (key points)". Such an exceptional but concise rendering of edited snippets.

i like your editing style, it keeps my adhd brain entertained

Replacing computation with caching. Clever caching, but it is what it is. This is the very first solution a programmer will use to computations taking too long. Can we cache it instead. Gaussian splatting is a way to cache rendering for use later. But it takes *all if the ram* to do it.

I've seen other, much longer, videos on this and wondered how it works. Now I know. After 2:11. This is the first time I pay money to show my gratitude. Great work. Keep it up! Liked and Subscribed. THANKS.

It'll be used for specific applications only. If you want to use that with video games you'll still have to give geometry to all the objects and environments, meaning it will still need to render all of that with polygons.

I wish everything on RU-vid was this concise.

well, how much vram do you need? and could nVidea's new compression algo's for regular texture streaming (a 4x savings on VRAM) help at all?

I love how short and concise this was. Well done mate! No BS, cut to the chase

I've never been at a higher peak of the Dunning Krueger effect in my life.

I saw something similar years ago with similar impressive results. (also just a point cloud being brute forced into a picture.) However, the downside of this type of technique is its memory requirement, making it fairly niche and hard to use in practice. For smaller scens it works fine, for anything large and it starts to fall apart. Beyond this we also have to consider that these renders are of a static world. And given the fairly huge amount of "particles" making up even a relatively small object, then the challenge of "just moving" a few as part of an animation becomes a bit insane in practice. Far from impossible, just going to eat into that frame rate by a lot. Most 3d content is far more than just taking world data and turning it into a picture. And a lot of the "non graphics" related work (that graphics has to wait for, else we don't know what to actually render) is not an inconsequential amount to work with as is. Moving a few tens of thousands of polygons around as a character model walks by isn't trivial work. Change those tens of thousands of polygons into millions of points (to get similar visual fidelity) and that animation step is suddenly a lot more compute intensive. So in the end, that is my opinion. Works nice as a 3d picture, but dynamic content is a challenge. Same for memory utilization, something that makes it infeasible for 3d pictures too.

It looks awesome, but my first thought is, how does real-time lighting match up in a scene like this? What if I shine a flashlight, or shoot a bright projectile, does my in-game prop - vehicle, person, gun - accept lighting?

This was amazingly well put together

Thank you for your objective presentation. Very interesting indeed. I'll check later for more.

10/10 intro, literally perfect in every way. I immediatly got what I clicked for and found myself intrested from 0:02 onwards.

Reminds me of Euclideon ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-iVsyB938ovY.html in the sense that animations seem difficult to do. Would you need to train the Gaussian splats for every bone / skeleton configuration? Do they interpolate well?

This video has "entire history of the world, i guess" vibes and I love it

This guy is too good for this level of subs... Subbed right away

Why can't ALL videos be as informative like this one in such a short span on time. Well done!

I wonder if something like this could eventually be combined with some level of animation and interactivity - in games that is. That would be wicked.

Wow, a techie faster talker who didn't lose me along the way. Excellent video!

Now this is that Enemy of the State "rotate the camera and zoom to the bag" surveillance scene.

I've always wondered about this. All my life since i started getting into videogames graphics from when I was a kid. I knew it had to be possible and watching this is like the biggest closure of my life.

WHY EVERYBODY DOESNT MAKE INFORMATIVE VIDEOS IN THIS FORMAT? Fast, clear to the point, no filler stuff, just pure info in shortest amount of time.

this is the first video from this guys I've watched and I'm hooked. Like, damn son.

Love this approach to explaining. Very fun to take in.

You're like Bill Wurtz without all the fun jazz

This video gave all the information neccesary in the shortest time possible while still containing entertaining editing. Bravo sir!😂