What an incredible time we live in where one of the authors of the paper can explain it to the masses via a public forum like this! Incredible and mind expanding work guys! Thankyou so much :)
@twobob2 жыл бұрын
popping the link to the videos in the description of the video would make a lot of sense. Enjoyed the nerf paper.
@codebycandle4 ай бұрын
...a good reminder to keep up w/ my pytorch studies.
@briandelhaisse1112 Жыл бұрын
Very good explanation! Thanks for the talk.
@SafouaneElGhazouali Жыл бұрын
Very nice work !! keep it up Drs.
@jeffreyalidochair Жыл бұрын
a practical question: how do people figure out the viewing angle and position for a scene that's been captured without that dome of cameras? the dome of cameras makes it easy to know the exact viewing angle and position, but what about just a dude with one camera walking around the scene taking photos of it from arbitrary positions? how do you get theta and phi in practice?
@alexandrukis77611 ай бұрын
These papers usually use COLMAP to estimate the camera position for every captured image for real-world datasets. For the synthetic dataset (e.g. the yellow tractor), they just take the camera positions from Blender, or whatever software they use to render the object.
@hehehe519811 ай бұрын
very good explanation
@cem_kaya2 жыл бұрын
thanks for sharing this presentation
@Patrick-vq4qz Жыл бұрын
Awesome talk!
@TechRyze Жыл бұрын
I'm curious to know - when he said at the end that he only has 3 scenes ready to show... considering he mentioned only using 'normal' random public photos - why would this be? Is this related to the computational time required to render the finished product, or for some other reason? If the software works, then surely, give the required amount of time and computational resources, this technique could be used on a potentially infinite number of scenes, using high quality photos sourced online. Is there a manual element to this process that I've missed here, or is the access to the rendering / processing time and resources the limitation?
@kefeiyao77842 жыл бұрын
Great explanation indeed. I have one question: is it ray tracing or ray marching? From the talk, I seemed to find it to be ray marching, but the actual phrasing in the talk was ray tracing.
@masonhawver3577 Жыл бұрын
Marching
@prometheususa2 жыл бұрын
brilliant explaination!
@SheikahZeo2 жыл бұрын
Nerf outputs transparency but all the demo videos seem to only have opaque surfaces. Does it actually work with semi-transparent objects?
@SheikahZeo2 жыл бұрын
The colour output will be constant along a freely propagating ray. Seems you waste time recomputing the whole network when you really are just interested in the density
@Cropinky Жыл бұрын
works that come after vanilla nerf deal with opaqueness better than the vanilla nerf does
@ritwikraha2 жыл бұрын
Excellent explanation!!!
@baselomari36572 жыл бұрын
Glad to see Seth Rogan successful with this career change.
@arcfilmproductions7297 Жыл бұрын
What's the difference between this and the 3d scans you get on an ipad pro? Apart from the fact this looks better. Just trying to get my head around it.
@hanayear4 ай бұрын
The English subtitles are not in-sync with the video !! someone please help 😭
@sirpanek32632 жыл бұрын
Do you see any use for this with drone imagery and fields of crops? This wouldnt work for stitching images im guessing….
@zjulion Жыл бұрын
nice talk. keep going
@yunhokim78462 жыл бұрын
This is super helpful Thank you so much
@mirukunoneko13758 ай бұрын
cc is a bit offset but overall is great!
@theCuriousCuratorML Жыл бұрын
where is that notebook speaker is talking about
@rahulor3773 Жыл бұрын
Please provide the link if you have it already.. Thanks in advance!
@darianogina148 Жыл бұрын
Could you please tell how to make NeRF representation meshable?
@seanchang28762 жыл бұрын
Hi, I'm just wondering how to know the ground truth RGB color for each (x,y,z) spatial location ?
@wishful97422 жыл бұрын
Hi, You don't need that data. The neural net produces the RGB and alpha for each point along the ray (that was emitted from the pixel along the view direction), then when we have all of ray points RGBA, we can obtain the final pixel RGB color using ray-marching (so all of the parameters along the ray results in the RGB of the pixel). And now we can compare the actual pixel from the obtained pixel and learn from it to produce better parameters along the ray.
@miras3780 Жыл бұрын
@@wishful9742 hi, may I ask how does exactly ray marching work? I am not sure how does MLP know that the scene is occluded at certain distance. Does it also learn sigma values from MLP? Or does the distance to the occluded point calculated from camera intrinsic and extrinsic properties? (I am new to nerf )
@wishful9742 Жыл бұрын
@@miras3780 Hello, for each point along the ray, MLP predicts the color and the opacity value. The final pixel is simply the weighted sum of colors (weighted by its opacity value). This is one way of raymarching and there are other algorithms of course. please watch 10:35 to 13:50
@melo27223 жыл бұрын
@24:42 he says "you can see the relu activations in the image"- what is he pointing to in the image?
@paoloceric64643 жыл бұрын
I think he might be referring to the flat areas (which would be the flat part of the relu)
@prbprb27 ай бұрын
Can someone give a link to the Colab discussed around 12:00
@jouweriahassan8922 Жыл бұрын
whats the difference between this and photogrammetry?
@anirbanmukherjee51819 ай бұрын
Intuitively the main difference is that photogrammetry tries to build an actual 3D model based on given images, while NeRF model learns what the images from different view points will look like without actually building an explicit 3D model. Not sure about this point, but Nerfs are probably better given a certain number of images
@norlesh Жыл бұрын
45:32 - "were never going to get real time NeRF" and then came Instant-NeRF ... never say never
@崔子藤2 жыл бұрын
I like it😃
@mattnaganidhi942 Жыл бұрын
Noice 👍
@prathameshdinkar2966 Жыл бұрын
I hit the 1Kth like!
@jimj2683 Жыл бұрын
One day these algorithms will be so good that you can simply feed all the photos on the internet (including Google Street View and Google images) and out comes a 3d digital twin of the planet. Fully populated by NPCs and driving cars. Essentially GTA for the entire planet.... With enough compute power there is no reason this will not work when combined with generative AI that fills in stuff that is missing by drawing experience from trillions of images/video/3d capture. Imagine giving a photo to a human 3d artist. He will be able to slowly make the scene in 3d from just the photo by using real world experience he has had. Here is a rule of thumb with AI: Everything a human can do (even if it is super slow), AI will eventually be able to do much much faster. Things are going to speed up a lot from here. Cancer research, alzheimer cures, aging reversal etc... Exciting times.