3D Gaussian Splatting! - Computerphile

A new technique to turn pictures of a scene into a 3D model is quick, easy and doesn't require that much compute power! Dr Mike Pound and PhD student Lewis Stuart demo and explain.

This video was filmed and edited by Sean Riley.

[jones]

"Posh Point Cloud" is the best best short description of Gaussian Splatting I've heard.

[yyanri]

I love this two person interview format. It’s so dynamic.

[CludWolf]

What I like most about Gaussian splattering is that it is basically a non neural network approach that is competitive if not better than neural network approaches.

[HereticB]

I love how in traditional computer science nerd fashion whenever either of them speaks the other one just looks extremely awkward, like they don't know what to do with themselves.
love the new format btw
seriously, do more of these
please

[wallyhall]

Eye contact makes a lot greater difference to the video than I would have guessed.
Really great content.

[OldShatterham]

love how enthusiastic Lewis and Mike are about these techniques!

[vesk]

This is so cool! I've been looking for a neat explanation on what actually Gaussian Splatting is for a long while now. And who better to explain it. Perfect!

[cazino]

I'm always pleasantly surprised when I see a computerfile video with Mike popup on my recommendations.

[zzzaphod]

0:23 and later, Humble Pi in the background of a video released on Pi Day, well done

[maxmusterman]

Yes ❤ please more videos about techniques like this. Also reeeaally enjoyed the 'old' computer vision and neural net videos. They inspired me to pursue a carreer in this direction! thank you

[makebreakrepeat]

I've been trying to understand this for so long 😅 Thank you for the clear explanation!

[davar_d]

Small correction 5:58
The 3D Gaussian's mean is indeed placed at the location of the corresponding SfM point as it represents the closely estimated position during initialization. The size of the initial isotropic Gaussian is determined by the average distance to the three closest neighboring points.

[petergerdes]

Is there a reason for using gaussians rather than, say, some kind of wavelets to allow automatic compression by rounding high frequency information?

[lpbaybee]

This is such a cool topic, and such a great explanation. Thank you!

[nicholaslck]

The energy and the passion here, wonderful!

[rich]

There is a certain fuzziness and artifacting that is unique to splatting which begins to be a bit of an eyesore the more you work with them. Almost like you are wearing googles with vasoline smeared in random spots. I hope we discover some way to overcome that. Maybe combining traditional and splatting and doing boolean operations to cull the splatting errors?

[danzmachinz]

Nice! SMERFs next! Or maybe how to generate a 3dgs point cloud from only 2 or 3 cameras?

[MarcAyouni]

I was always a bit put out with NERFs, since a scene is a NN and all the problems that this entails. GS has such incredible potential.

[TheJacklikesvideos]

you two drawing pictures of pine tree renders reminds me of the brothers drawing the trees in Myst by smearing big green cones.

[syjwg]

What a nice explanation! We've come a long way from the ray tracing in the early, but at that time, mind-boggeling 'Wolfenstein' or 'Doom' engines.