Пікірлер
@ngocnguyen9517
@ngocnguyen9517 Ай бұрын
You're talking like you worry the audiences will understand your paper
@dylanSmith-r5h
@dylanSmith-r5h Жыл бұрын
the project link is currently unavailable. Could you please share it again? Thank you very much.
@UTKARSHTIWARI-v4o
@UTKARSHTIWARI-v4o Жыл бұрын
what app is being used to capture images in the correct position/ at 1:30
@FredPauling
@FredPauling 2 жыл бұрын
The paper that started a revolution.
@alhdlakhfdqw
@alhdlakhfdqw 2 жыл бұрын
really awesome video thank you so much! great work :)
@user-oj4hr5rh6i
@user-oj4hr5rh6i 2 жыл бұрын
😮
@xiaoyanqian6898
@xiaoyanqian6898 2 жыл бұрын
Hi, thank you for the great work. I just wonder what software you used to make this video that could vividly show the iterations, the Fourier features and its Std, frequencies, and reconstruction.
@brainlink_
@brainlink_ 2 жыл бұрын
Thank you so much for this wonderful video!
@brainlink_
@brainlink_ 2 жыл бұрын
Thank you so much for this wonderful video!
@yifeipei5484
@yifeipei5484 2 жыл бұрын
You can just use Discrete Cosine Transform to do it. We have a paper: www.cse.scu.edu/~yliu1/papers/ISCAS2020Yifei.pdf
@TheMcSebi
@TheMcSebi 2 жыл бұрын
Stunning
@sapiranimations
@sapiranimations 2 жыл бұрын
Would it be feasible to somehow incorporate the fourier features in the activation functions? So that the entire model can be made high frequency sensitive instead of just the input
@yifeipei5484
@yifeipei5484 2 жыл бұрын
You can just use Discrete Cosine Transform to do it. It's much simpler. No need to use Fourier transform to make it complex. We have a paper: www.cse.scu.edu/~yliu1/papers/ISCAS2020Yifei.pdf You can write 2D-DCT into 1 dimensional representation for activation function. See our another paper: www.cse.scu.edu/~yliu1/papers/ISCAS2021YifeiPei.pdf
@yifeipei5484
@yifeipei5484 2 жыл бұрын
However, these transforms can only work on fully-connected neural networks. It gives bad results on CNN.
@pratik245
@pratik245 3 жыл бұрын
Such a new concept.. No body really thought about it before them. How genious!!
@BenEncounters
@BenEncounters 3 жыл бұрын
Could this technique be combined with photogrammetry to be able to represent reflective and plain surfaces as well as people?
@snowjordan6822
@snowjordan6822 3 жыл бұрын
Wow
@sheevys
@sheevys 3 жыл бұрын
How does it compare to NeRF?
@alexeychernyavskiy4193
@alexeychernyavskiy4193 3 жыл бұрын
Great video, especially the part with the scale is well explained
@Benjamin-il8vf
@Benjamin-il8vf 4 жыл бұрын
Good channel. Looking forward to seeing more from you! By the way, go and search for SMZeus . c o m!! It will help you promote your videos!!
@alfcnz
@alfcnz 4 жыл бұрын
Nice work and good presentation. Just a couple of questions, though. At 5:59 you define the loss as using the function “render” which has never been defined here or on the paper. Can you please clarify where it comes from? Thanks. Also, at 4:46 I understand that C = 𝔼(c), with c vectorial output of the net, following the cumulative opacity, function of σ, output of the network. Is this correct?
@oOXpycTOo
@oOXpycTOo 3 жыл бұрын
I guess, render function means just computing the color of an image at a particular pixel, using the formula, defined in kzbin.info/www/bejne/goOkopiDbaqdhdE
@crazyfox55
@crazyfox55 4 жыл бұрын
A+ in my book.
@ChrrZ
@ChrrZ 4 жыл бұрын
incredible!!
@othoapproto9603
@othoapproto9603 4 жыл бұрын
a solution looking for a home, Rick Deckard would approve
@zhenyujiang9574
@zhenyujiang9574 4 жыл бұрын
At 9:07, the reflection on the TV screen is also changing accordingly. That's really amazing!
@МаксимЗубков-ь4ъ
@МаксимЗубков-ь4ъ Жыл бұрын
what did you expect, it was present in the input images. for the code, there should be no difference between the reflection and the 2nd room behind the tv
@nikronic
@nikronic 4 жыл бұрын
You might not believe, but 6 hours ago, I suddenly decided to read your amazing work! now I am here! Thank you
@jcjensenllc
@jcjensenllc 4 жыл бұрын
In about the fourth set of samples there is a dinosaur skull ( on bottom row) that had serious flaws. Please explain why that one failed.
@importon
@importon 4 жыл бұрын
Is there a google colab notebook we can try this out with?
@jkickass
@jkickass 4 жыл бұрын
ok but what am i going to do with wobbly 3d images?
@jonathanl2757
@jonathanl2757 4 жыл бұрын
Please add vertical capture to fyuse for those of us who are passionate about our captures!
@chasemarangu
@chasemarangu 5 жыл бұрын
wow
@DenisVostrikov
@DenisVostrikov 5 жыл бұрын
Impressive demonstration of mathematics knowledge. But it is more practical to shoot video for the best result. Isn't it?
@user-vh9kw6gc9y
@user-vh9kw6gc9y 5 жыл бұрын
the matrix had always been, the only possible goal
@Veptis
@Veptis 5 жыл бұрын
Can you capture input data from a video? Would this work with non RGB images? Monochrome or even something like low resolution thermal imaging (320*240)
@mauriciopereira4824
@mauriciopereira4824 5 жыл бұрын
Empolgante! : )
@bruce_luo
@bruce_luo 5 жыл бұрын
Wow. And this video itself stands out for its quality too.
@polytrauma101
@polytrauma101 5 жыл бұрын
Very promising results, great work! Is this method potentially applicable to 360° lightfields?
@andrews4030
@andrews4030 5 жыл бұрын
is it possible to catch instant processes by this method, I mean splash of water or fire??
@gregkrazanski
@gregkrazanski 5 жыл бұрын
i assume if you had 25 cameras in a semi-regular grid that all took a photo instantly, it would work
@lilboi3000
@lilboi3000 5 жыл бұрын
This is so awesome!!!! Also didn't realize you were at Berkeley until I saw that fern, that's VLSB isn't it haha?
@games528
@games528 5 жыл бұрын
Make this into a phone app and become rich.
@Geddy135
@Geddy135 5 жыл бұрын
any chance on someone making an app for this? or even just a more streamlined program to use on desktops?
@Wiiplay123
@Wiiplay123 5 жыл бұрын
Really wish there was a Windows port :\
@amoose136
@amoose136 5 жыл бұрын
Possibly as the code is open source and has 100+ stars. Keep in mind it’s a remote possibility and all of these tools typically aren’t even shared.
@RivenbladeS
@RivenbladeS 5 жыл бұрын
In what subjects is these techniques useful? What do they solve and where will you use them?
@Wiiplay123
@Wiiplay123 5 жыл бұрын
@@RivenbladeS They didn't really go over the uses of light fields in the video, but it's really good for VR kzbin.info/www/bejne/hYa4Y6x9fcyDh7s
@jonathanl2757
@jonathanl2757 4 жыл бұрын
Fyuse app is a limited implementation
@gaussianguaicai
@gaussianguaicai 5 жыл бұрын
It’s soo cool to capture local light field by using just a mobile phone , I tried the google spherical light field before, clearly this has the quality to compere it.
@shrillcacophony
@shrillcacophony 5 жыл бұрын
Outstanding! Have there been any explorations into how your method would work with camera arrays--perhaps including video camera arrays?
@benmildenhall3169
@benmildenhall3169 5 жыл бұрын
It works very well on the 5x5 camera array data collected by the authors of Soft3D (ericpenner.github.io/soft3d/). We have not found any public video camera array data to try it on yet, theoretically it should work, though practically the size of the output MPIs might become an issue when reconstructing more than 1-2 seconds worth of data.
@infiniterealities4D
@infiniterealities4D 5 жыл бұрын
@@benmildenhall3169 Incredible work. We might be able to supply genlocked high-resolution video data. Can you work with larger arrays? What image resolution would you prefer? And do you have any technical preferences for camera spacing and orientation?
4 жыл бұрын
@@infiniterealities4D Wow the fact that IR sees potential in that means it's really as clean of a technic as I thought.