NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (ML Research Paper Explained)

Crazy to think that this came out 2 years ago, advancement in the field is crazy

Python code?

Thank u😮😮😮😮😮 amazing description

My guy, this has to be the best tutorial on NeRF I've seen, finally understood everything

Amazing video, thanks a lot.

Phenomemal video!

Pretty clear and great thanks to you!!

Beautiful and Super Intuitive video ! Thanks :3

This is an amazing explanation! I have a doubt though. You talked about the major question of training images not having information about "density". How are we even computing the loss in that case for each image? You said we compare what we see with what the model outputs. But how does the model give different density information for a particular pixel if we don't have that kind of information in the input? How will having a differentiable function that can backtrack all the way to the input space be any helpful if we don't have any reference or ground truth for the densities in the training images?

Loved the video. Learned a lot. Thanks

Is this an in depth breakdown of what photogrammetry or is this different?

Thanks for the explanation!!

I was searching for nerf guns, this is better than what I was asked for.

I think, saying that each scene is associated with one single neural network (NN is overfitted for that scene) is not correct.

bro you are killin' it, pretty damn good explanation thanks

so there are really two networks (coarse and fine) or this is some kind of trick ?

One of the best NeRF explanations available. Thank you so much, it helped a lot.

Great video. Can you please make one on LeRF (Language embedded Radiance Fields)?

Its ilke end of the photogrammetry

THE BEST

It’s NeRF or Nothin’ 😎

Code?

Gotta present this paper for a seminar at uni so this video makes it so much easier. Thank you so much for this!

Awesome explanation! Please dont stop making these.

Man you got many clear notes to explained papers. I got tons of helps from your videos.

You could stack lots of objects so long as you know the transformation from object to world coordinates and give each object a bounding volume in world space for the ray tracer to bother calculating if you had a supercomputer you could render worlds with thousands of overlapping and moving objects :D

Thanks for the Great explanation. Finally understand the central ideas behind NeRF.

Great video. Thanks Yannic!

I noticed manny of the scenes were from UC Berkeley, kinda trippy. The engineering school there gave me a bit of PTSD ngl.

This sounds as if presentation could be entirely done in a raymarching shader on the GPU as I suspect the evaluation of the model can be implemented as a shader.

But can this be used real time?

This is mind blowing

This type of pre-digestion for a complex technical paper is very expedient. Thank you.

awesome video! Really appreciate you doing this!

Thank you for the clear-cut and thorough explanation! I was able to follow and that is definitely saying something because I come from a different world, model-based controls :)

finally something without cnns. bravo guys.

Really cool. I love getting into this stuff. I'm a compsci student in my first year, but considering switching and going for AI. Such an interesting field.

What a time to be alive! ;)

This video helps a lot for some fresher like me to understand NeRF, thanks!

Thanks to your markings and visualization I can understand a lot more than I could on my own :D

Hi Yannic, I found this video very helpful. Could you do a follow up on instant NERF by Nvidia?

When will this become available for image/video software?

Help! How do they determine depth density from a photo? Wouldn't you need prior trained data to know how far away an object is, from a single photo?

what do you think the next step after NeRF?

Nice explanation!

Great explanation. Yannic! Like to know if this technique could be used for 3D modelling?

Why is this “overfitting”? Wouldn’t overfitting in this case be if the network snaps the rays to the nearest data point with that angle and doesn’t interpolate?

Excellent explanation. Realtime 3D Street View should be right around the corner now.

非常细致的讲解，thanks to you!

Awesome explanation! Thanks for the video.