3D Gaussian Splatting - Explained!
Vložit
- čas přidán 13. 05. 2024
- Gaussian Splatting is taking the world of 3D graphics by storm. Learn how this revolutionary technique can render photoreal scenes in real-time for cutting-edge applications. Discover how it works under the hood to optimize discrete gaussian "splats" instead of slow neural rendering.
But it's not just the speed (100+ fps!). See how the discrete representation also enables direct editing! And find out how early adopters are creating stunning demos. Needless to say, visual effects potential is off the charts :)
This video covers all the core concepts you need to understand Gaussian Splatting and why it is the most promising advancement in computer vision and graphics. I got numerous questions about it on Twitter so I decided to make this deep dive. I hope it helps you stay ahead of the curve and boost your skills!
00:00 Gaussian Splatting Overview
00:17 Why Is Gaussian Splatting Awesome?
02:35 What's Happening Under The Hood?
04:00 Step-By-Step: Building a Gaussian Splatted Scene
06:27 Conclusion: The Future of 3D Graphics
- original research paper: huggingface.co/papers/2308.04079
- step by step blog: www.reshot.ai/3d-gaussian-spl...
- technical deep dive: • Gaussian Splatting exp...
Connect on socials:
- Twitter/X: / bilawalsidhu
- Creative tech digest (weekly newsletter): creativetech.beehiiv.com/
- Other links: beacons.ai/billyfx
#ai #3dgaussiansplatting #3dscan #gaussiansplatting #3d #3drender #photogrammetry - Věda a technologie
Really great stuff, man -- love the in-depth breakdown done in a conversational manner. Looking forward to seeing your channel's growth!
This can be used to google maps street view. Imagine instead of clicking arrows to move forward, you just need to press “w” maybe as if you are walking in a video game
Exactly
Maybe too expensive and big for the whole world
@@hallo_ween07 Starting with a town maybe? Then slowly moving towards a country? Maybe a different type of google car can be made to use photogrammetry instead
Wow, that's truly impressive! Thank you for this video
it explains everything so well Keep up the good work!
Great explanation, love the video quality. Cheers
I stumbled across this video and I'm blown away.
In a former life I use to do a lot of graphics and old-school 3D work. Could I request a beginner's guide on "how to get started" with the tech you covered?
Very comprehensive explanation, I actually do research on these reconstruction and view synthesis topics and your intro explanation made it very clear where/how to start thinking about gaussian splats.
Much needed information, short and crisp, thanks Bilawal
Really awesome video and how you explained it - clear, crisp, in-depth. And thanks for including links to further resources.
Nice vid bro. I love your editing style
I've discovered the topic today and my mind is blown away
Amazing video! Really exciting applications for this!
Brother your channel is going places. Your content is presented in a very straight forward manner and will get you far. Keep at it. See you at the 1 million Sub mark.
Perfect video, thank you very much. It denotes main paper ideas and help me understand paper even more
Very clear explanation. Thank you.
Very Well explained! Now I really understood the spherical harmonic part of this tech. Thank you.
It really is the cherry on top, and love that an OG physics concept helps pull it off!
Hands down the best explainer I’ve found about Gaussian splatting - super clear and understandable without compromising any technical accuracy!
Thank you Ashwin!
the editing quality is dope!
Fantastic! This level of detail is candy for Gaussian Splatting devotees
Thanks! I’ve been wondering if I go more high level but I think this might be the way to go
Great breakdown man! I definitely have a better understanding now. :)
Is this explanation the one?! 😂
This is a great explanation for guass splat !
Amazing explanation for those working in 3D. Thanks
My pleasure!
Bravo Bilawal! Well done. Straight to the point why GS is such a promising approach. I especially enjoyed the comparison to the "wonky looking broccoli trees" ;-)
🥦 🙈 you know all about it 😂 great to see you!
This is a great explainer - thank you!
Glad you enjoyed it!
Amazing, thank you!
Gosh this is insane progress
WoW 🤩-it’s doesn’t get any better!
If you use enough buzz words and look around the room you can sound like you know what you're talking about. Good job.
Great way of explaining it
The best video on the topic so far and with well represented insights.
How would you see Gaussian Splats in the construction industry?
Excellent job!
Thank you! I think the photogrammetry tools had largely written off Nerf as a fun research toy. Gaussian splatting is making them pay attention and I could see it quickly become a common artifact alongside other reality capture data products in AEC. Amazing for visualization and progress snapshots!
Would be Interesting to see applications dealing with heritage preservation demands considering we’re typically using Point Clouds. If we could see GS as a resource for model driven Digital Twins and other digital processes for maintenance operations, I think we can cut away hundreds of hours of modelling work.
Thanks. Can you make a video of how this can be used for product marketing. Like creating a 3d structure of a product for websites. Can you also confirm if this can be done using some mobile apps
@@shoaibwaqar9477it’s a great use case, def possible. For mobile check out Luma AI and Polycam
Amazing tech 💜. Bilawal really makes the inner lost 3d kid in me resurface 🚀
Great Video👍🏼
Thanks B!
Great work breaking things down Bilawal! Nice job
Means a lot coming from you! Miss ya G ❤️
Excellent work! 3dgs can be used for any presentations, including those for ordinary consumers, real estate agents for project visualization, doctors, VFX/CGI, artist....
Thanks! Agreed - huge potential for many verticals
What a legend you are mate! Thank you for this great content
Extremely fast but caught up with mind-boggling information.
This is insane
Great vid, I subscribed. Could you do a vid on dynamic NeRF (DyNeRF)
Will this ever work for video? Could you combined multiple angles of a speaker or actor and create a moving Gaussian splat video? Great video!!
Should I re-name from MESH IMAGES to GAUSS IMAGES?
Great video, looking forward to the next one!
Ngl I kinda like gauss images way more than “gsplats” or “GaSp” 😂
this is genuinely the best explanation i've heard on gaussian splatting. especially the part i don't think i've heard anyone talk about that is HUGE, which is *spherical harmonics*. actually showing reflections and the sun through the leaves that you're showing here. massive.
Please make a video about cloud editing tools and point cloud shaders with Gaussian Splats. Thanks!
*takes notes*
now i just wish to see some kind of style filters. since it uses point clouds, we definitely have depth as a parameter, giving us stuff like edge highlighting or idk, zoom effects. Could probably train a stylized cartoon filter. Since the splats are mostly gradients, maybe flatten the colors to specific styles?
Would be fun to mess with if my PC would be able to process all the stuff :/
Def doable. Check this out: twitter.com/johnowhitaker/status/1696336230299185647
Interesting
"Insane, unbelievable, amazing, oh my god"
What is the best gausian splatting software for using drone footage. I have the original DJI MINI so I can't plot routes. I'm assuming video to luma ai would be easiest
Thank you, that was clearly explained and very exciting. A very minor quibble is that Gaussian splatting is named for one of the greatest mathematicians of all times. His name is pronounce gawse and the curve he discovered is called the gawsian and is central to the study of probability and statistics. And now, computer graphics!
Thank you, and duly noted on pronunciation!
i am confused, watching the video right now, and the pronouciation sounds very typical american? i think its good, whats to complain?
the real pronouciation of course is difficult for non german speakers, listen here en.wikipedia.org/wiki/File:De-carlfriedrichgauss.ogg
@@sirletoare you able to say "house" or "mouse"? You don't need to be German to pronounce Gaussian correctly!
@@sirleto I don't want to make this a big deal. Mathematicians and physicists all pronounce it this way and thought you might care :) @daverayment explains it better. Gauss rhymes with house.
nice
How do you use an FPV control to move around? That looks really great
The viewer on the 3DGS inria GitHub - also unreal engine itself works for such FPV controls!
I think 3d video's will also be a great thing when they are ready?
I just have seen a demo of a video that probably had a depth map, so it was a 2d video but made 3d. But when you went behind an object to the side where there was no camera, then there was no object.
I think AI could automatically predict what is behind an object and in that way create 3d maps from just normal videos.
Then you could watch videos and walk around in those video's. I think this will be amazing.
Spot on - I think this is the direction apple seems to be going. Do more sophisticated infilling of a parse 3D capture
Have you heard about anyone/any tools to convert a poly environment to a GS one and then compare the results?
I was trying to find the origin and interpretation of the term -Gaussian Splatting. Does anyone know why it is called like that?
Do you know or this also possible with scans made by the matterport pro 3?
Maybe. I don’t believe the density of those RGB scans is good enough unless you really put the tripod in a bunch of locations. Though I guess matterport could try to use their depth data in the training process to make up for that sparsity?
This is a very interesting and educative video , my question is that what software can you used for the point cloud which software is the best
For the initial sparse point cloud / posing of images - colmap is fine but reality capture, Agisoft Metashape, etc would be better. Google also released CamP code this week which is also bette than colmap.
How about the camp can u pls help me with the link so that I will download it on my dell laptop
How about the camp can u pls help me with the link so that I will download it on my dell laptop
@@ibrahimsalisumadaki678 camp-nerf.github.io
Wow such a good video. I don't need to read the paper anymore
Glad you found it helpful!
Counting minutes until a vr game releases with this.
I too am wondering how this could be used for capturing 3D models (e.g. as part of a 3D printing workflow)
If you want metric accurate continuous surfaces; splatting may not be ideal for your use case. It’s much more suited to “view synthesis tasks”
Imagine having a 3D rendering engine that can automatically harness the power of Gaussian splatting for 3D animation, rendering only the needed Ray traced frames to create the splatting and turbo charge the rest of the frames making it possible to render long animations on a single consumer machine in record time.
Love this. I think this we’ll get tools like this sooner than we think - 2024 is gonna be a fun one
This tech now looks so close to what Brain Dances look on Cyberpunk 2077
I'm wondering about the spherical harmonics. I really didn't understand how that part works.
I suggest watching the linked video as it goes into a lot more detail on how the spherical harmonics are implemented
But how do Gaussians show spherical harmonics? Is it a mono colour blob that fades away or does it have many colours showing at different angles?
class Gaussian:
def __init__(self, center, scale, covariance, color):
self.center = center
self.scale = scale
self.covariance = covariance
self.color = color
#Is this enough? Or is there more to it to attain spherical harmonics?
Please do a Maven course…😊
Potentially. If enough folks are interesting in something dedicated to 3D capture
Can't this be done with transparent polygons? what is the size of Gaussian splat. About 50 bytes? How do Gaussians splats render faster than polygons?
Spline added Gaussian Splatting today. So it’s real-time for the web.
Gauss-ian, it's named after Carl Friedrich Gauss
Is it possible to measure inside?
Gaussian splatting is good for view synthesis. For real world measurements - you’re better off using classical photogrammetry to densify the point cloud or turn it into mesh and measure that. Of course you need to make sure your scan is metric accurate and to scale. iPhone apps that use the AR metadata eg Polycam do a good job of automating that for you.
Welcome to new UE Plugin: "UEGaussianSplatting: 3D Gaussian Splatting Rendering Feature For UE"
It can replace NeRF?
It seems NeRFs are punching back nicely
czcams.com/video/Olos5h8fmXE/video.html
I would be interested to see if this improves the quality of splatter movies…
Great video! One pet peeve: it's pronounced gau-see-uhn
Thanks! That’s how learned it picking up photoshop as a kid in India lol. Fixed in new video :)
Very cool. How do I photograph a dragon though? Or Aliens?
There’s a ton of interesting research that uses radiance fields as the 3D representation but diffusion models for the generation. Quality isn’t quite where MJ is for still imagery tho!
Could you render a 3D scene into Gaussian Splats for more rapid playback in game engines? I imagine if you could you could purposefully distribute the points intelligently, creating a better looking final result.
Interesting. Reminds me a bit of what Google Seurat was trying to do
So...how much will it cost me to get into this game? All I've got right now is a reasonably capable PC, a few VR headsets I would like to view this stuff in, and a bit of free time.
Not much at all. Use your phone to capture and process in the cloud with luma or polycam. Drop ‘em into Unity and check it out in VR!
I have a question that almost certainly reveals my total ignorance of this tech! When rendering 3d GS environments in a game engine, is it concievable that game mechanics could be added to this, for instance, pathfinding, collision, decals, all that traditional 3D stuff.
it's still early days. you could certainly query metadata you attach to each splat. you could also mix and match - make a mesh version using photogrammetry but keep the visibility off but keep it on for physics collisions, path finding etc.
*@Creative Tech Digest*
0:11 No, I have no idea what any of those words means, and several other words, THAT was why I went to this video in the first place, to learn more, but I just get to hear a lot of meaningless words. :(
This is good feedback. I have added a “3D Capture 101” video to my queue! This video def assumes you know the basics of photogrammetry and 3d scanning tech
I... I think my degree is already outdated
Gosh, everyone feels that way lately no matter the degree. The fundamentals still matter tho so you’re good!
Fluid simulation should be faster with Gaussian splatting.
Great video! Btw, I’m 99.99% sure it’s pronounced gow-see-uhn.
somebody explaining from non 3d background. ??????
0:17 reaons
but it doesnt have any geometry....
it's a radiance field so that's a feature not a bug - instead of rasterizing triangles as you would with a triangulated 3D mesh for example - you instead rasterize these gaussian splats. you can still use a mesh under the hood if u want for collisions etc.
Thought it was mfing Kanye West on the thumbnail💀
😂 never gotten that before but I’ll take it
all this for better c0rn
It's useless if you can't generate a 3D mesh, something I can take into Blender.
There’s a simple plugin for blender but it won’t be a mesh. That would defeat the purpose of creating a radiance field in the first place.
@@creativetechdigest It's more useful as 3d mesh, there is no way to edit and modify radiance fields.
Good stuff but you’re pronouncing Gaussian wrong