Johannes Kopf

Пікірлер

@cg.man_aka_kevin 9 ай бұрын

How to do this???

@10bokaj 11 ай бұрын

Is it available somewhere?

@riniaahmed20 Жыл бұрын

Can I get the code of this project?

@jens111 Жыл бұрын

Wow, this is ideal for terrain texturing!

@ske2004 2 жыл бұрын

this is so useful!!

@dennisjaciw 2 жыл бұрын

Horrible!!!! 💩

@Kopsirtube 2 жыл бұрын

how can I use the resulting depth map for creating blur effect? davinci, sony vegas, premiere.. etc ?

@jasonbird5005 2 жыл бұрын

Soooo cool!!!! That look at older photos is awesome. But I will say I took a photo of a tree recently and posted it, and the AI went for the foreground, leaving the tree looking rather flat in the background. Crazy how technology works. Your almost like a puppet master.

@Isti115 2 жыл бұрын

It's amazing to see what research went on in the background that enables such complex solutions! I use the app on my phone from time to time and the results are often very good!

@BlakeEdwards333 2 жыл бұрын

Thanks for sharing!

@ericbernardo5317 2 жыл бұрын

what is the name of this software?

@danrandom408 2 жыл бұрын

Nice

@FordTransitvan 2 жыл бұрын

Can't understand a word

@wiiu7640 3 жыл бұрын

I'm having problems getting it to work. It says that I am missing dependencies but I have made sure to follow the instructions carefully. Could someone post a setup video so I can make sure I'm doing it correctly? I run Windows 10 on my machine.

@TheSamucacs 3 жыл бұрын

can u make a software with all bundled? its hard to set all things up

@steves5476 3 жыл бұрын

Soooo... where can I use this next time I go out?

@hamzatatheer 3 жыл бұрын

wish i could learn from u guys :')

@jayvallo3016 3 жыл бұрын

how can i use the program

@shawn3d 3 жыл бұрын

Hi Johannes, is there a way to use this to extract depth maps from video from a consumer standpoint? I want to be able to create depth maps from video to and depth of field in After Effects. Is there a way I can work with this software. Your help will be greatly appreciated :)

@differentone_p 3 жыл бұрын

can we do this with photos from google maps?

@shumshersubash 3 жыл бұрын

Does the repo have code for injecting 3D objects in the video as in 0:50?

@喬冶 3 жыл бұрын

非常美

@Alpha17x 3 жыл бұрын

This is awesome. too bad it won't be something I can use on a creative basis for like 15 years probably. (because cool stuff takes forever to get integrated into anything.)

@felix-dk9tr Жыл бұрын

Be the change you want to see

@myelinsheathxd 4 жыл бұрын

This is the most crucial TECH for AI learning, we give a game from any game store to train, then they learn VISUAL WORLD without leaving silicon

@yolomuffins1437 4 жыл бұрын

impressive, this is the same technology used in the skydio 2 drone for obstacle avoidance

@serhatkuk4180 4 жыл бұрын

Well done.

@ajay6225 4 жыл бұрын

Can we do in one cameras

@antoniocottone5382 4 жыл бұрын

this method works with static images too?

@user-cw3nb8rc9e 4 жыл бұрын

3:10 Here you could extract depth of the scene from perspective, by comparing how fast pixels and certain features move in the foreground and how slow in the background. I am surprised that river and everything came out so weak, almost invisible in the depth map. With the technique I described it should work very good to improve this.

@user-cw3nb8rc9e 4 жыл бұрын

By the way - are you able to extract more depth from faces and human bodies, generally objects? It seems faces and human bodies are rather flat here. Am I right? Many solutions make things work by extracting moving elements from the scene, but these still look like 2D posters on 3D background. Your stuff here is very good, but still I notice there is no great detail in depth of the scene. Can you, will you improve this?

@user-cw3nb8rc9e 4 жыл бұрын

Hi. Could you please make a walkthrough on youtube, how to use your github code on PC with Geforce card? I am sure lots of people would love to experiment with this 3D depth.

@xanthirudha 4 жыл бұрын

Is this using Light Field Synthesis?

@Ponk_80 4 жыл бұрын

This would be interesting to use on microscope and telescope pictures.

@albuquerquepioy7071 4 жыл бұрын

Hello

@CosmiaNebula 4 жыл бұрын

Here's an idea. Feed it a photo of a something standing in the center, and continuously rotate around it. See what the algorithm would hallucinate for the backside! Because if it can imagine moving the view angle by 5 degrees, I could take the photo with a 5-degree rotation, and apply the algorithm again, and again, until I get a full rotation. And we get a kind of "exquisite cadaver" video. I tried the Weights and Biases colab notebook, but got stuck. If you can do it, please try. Some ideas: Holding a globe blog.blogthings.com/wp-content/uploads/2013/01/woman-holding-globe.jpg Random person standing in a field. blog.theretreat.org/hubfs/images/Man-Standing-in-Field.jpg?t=1473880856264 Bottle of cola (can't find a good picture) Hot air balloon cdn.britannica.com/84/158184-050-1D7ADEB5/balloon.jpg

@SirPytan 4 жыл бұрын

The Problem is, that the in paint is only a rough estimation, and therfore the results would get worse with every extra angle and the more inpainting is needed. Also there is a lot of depth information missing as well, so forget a one shot solution for this. There exist AIs that can estimate room geometry only by looking from a few different angles at something, that would be a better solution, as well as using more sensors on a phone if availabel to increase the quality, like Apples Lidar sensor and so on. But still for everything that needs estimation and prediction it depends on how much data you have, if the result will look good or not and how well the prediction algorithm is.

@StefanPerriard 4 жыл бұрын

Absolutely amazing! Launch it as a smartphone app or desktop version

@StrangerHappened 3 жыл бұрын

Still nothing though.

@naorg1455 4 жыл бұрын

When is this app available?????? (either for purchase or whatever)

@Johanns0r 4 жыл бұрын

It's in the normal Facebook app! You can use it today on iPhone and Android.

@naorg1455 4 жыл бұрын

@@Johanns0r where can I get the link?

@naorg1455 4 жыл бұрын

@@Johanns0r I'm looking for it but can't find it

@naorg1455 4 жыл бұрын

@@Johanns0r I don't have the "make 3d" option

@megaz0rd 4 жыл бұрын

Is there any practical application of this method? Looks really awsome!

@importon 4 жыл бұрын

Impressive once again! is there a google collab notebook to try it out?

@Johanns0r 4 жыл бұрын

Hey, thanks. It’ll take a short while before we can release the code, but we plan to do so, eventually. I’ll let you know here when it happens.

@bioshazard Жыл бұрын

@@Johanns0rExtremely cool project! Code still on the way?

@souslicer 4 жыл бұрын

The novel view cannot shift too far from the source view?

@Johanns0r 4 жыл бұрын

Yeah, that’s the typical problem with approaches like this. The method should do well as long as you’re staying close to _any_ of the input views. But we’re not hallucinating any unobserved parts of the scene (yet! ...stay tuned :) )

@erenbalatkan5945 4 жыл бұрын

@@Johanns0r Impressive stuff! I was just thinking of DL based Async time warp for wireless VR headsets. You could technically try to estimate the position and rotation users head will be at at the point where display updates and time warp onto future point from rendered frame, if stars align, that could produce 0 latency image even eliminating the display update latency! I would have loved to do research like that but obviously one needs a very specific data for something like that.

@RANDOM-em6bv 4 жыл бұрын

This cat is legendary

@NerdyRodent 4 жыл бұрын

Nice work and MIT licence too. What a time to be alive!

@omhr9554 4 жыл бұрын

Impressive!

@nils2868 4 жыл бұрын

Does this work with video where the camera isn't moving?

@Fopenplop 4 жыл бұрын

"Well, first I draw this head, then I erase some of the more detailed features, and 1-2-3, a circle-! uh... thingy..."

@MichaelSavidgeStoryteller 4 жыл бұрын

Wow, this would be great for converting 2D video to Stereoscopic 3D! Thank you so much for all the hardwork you and your team has put into this code!

@dudegalen 4 жыл бұрын

how do i use this to create an alpha channel mask

@importon 4 жыл бұрын

Fantastic! This is active on FB right now? Can a user view the depth map? Is that accessible in any way?

@Johanns0r 4 жыл бұрын

Yep, it's in the FB app. Give it a try! I am afraid there's currently no way to export the depth map, but you could use, for example, a method like Midas to estimate depth maps for your images.

@importon 4 жыл бұрын

@@Johanns0r Just updates my app and it looks like I don't have the option. Do I need a particular model of phone?

Ең жақсы KZbin

Пікірлер