Johannes Kopf

Vision / Graphics / ML Researcher @ Facebook Reality Labs

[Johannes Kopf @JPKopf]

@keenanisalive Have you tried talking to the reviewers? Sounds like a misunderstanding that can be easily resolved in a private discussion… IME people on the IPC are very reasonable.

[Johannes Kopf @JPKopf]

@DavitSoselia_ @jbhuang0604 @chrlaf @gaochen315 @ayush29feb If I remember it right we tried 20 videos. Out of these COLMAP failed on 10. Out of the remaining 10 these 6 were somewhat good enough to use in the teaser. For some we had to reduce the amount of induced parallax to avoid it looking distorted.

[Johannes Kopf @JPKopf]

Also, look at those reflections!!! 😊

[Johannes Kopf @JPKopf]

Bullet-time on any video!

[Johannes Kopf @JPKopf]

Bullet-time on any video!

[Jia-Bin Huang @jbhuang0604]

SUPER excited to share our work Dynamic View Synthesis from Dynamic Monocular Video! Check out our fun teaser video 😎!

Paper: https://t.co/V8819QX12n
Project: https://t.co/eYjqxdzvzP
w/ @gaochen315, @ayush29feb, @JPKopf

[Johannes Kopf @JPKopf]

No one can stop you from trading Dogecoin!

[François Chollet @fchollet]

People who say $GME is overvalued don't understand the value proposition. It's no longer a stock, it's a store of value. It's the new digital gold. And for now it has only 3% of the $BTC market cap, still plenty of room to grow. My price target is over $9,000

[Johannes Kopf @JPKopf]

@jonathanfly Agreed, it’ll be a game changer for VR! „Baking“ these into representations that can be rendered in real-time is an interesting engineering problem, but can totally be done. Actually, Google had a cool paper on this recently: https://t.co/rSQLNFgmkN

[Johannes Kopf @JPKopf]

Our latest work on making Consistent Video Depth more ROBUST. Works great for casual phone videos that are really difficult for previous methods.

Another great collaboration with @jastarex and @jbhuang0604.

arXiv: https://t.co/pVuruyAIt9
Project: https://t.co/Lvi3Ls5wzm

[Johannes Kopf @JPKopf]

Suckers like me only buy bitcoin at the all-time high... 🤦🏻‍♂️

[Frank Dellaert @fdellaert]

Space-Time Neural Irradiance Fields (https://t.co/vuiGScHOL3) simply use time as an additional input. Carefully selected losses are needed to successfully train this method to render free-viewpoint videos (from RGBD data!).

[Johannes Kopf @JPKopf]

You can try this algorithm *right now*, on your own phone, with your own photos. It's integrated in your Facebook app! :)

[Johannes Kopf @JPKopf]

Thank you for the beautiful coverage of our paper, Károly!

Find all the details about the work here:
https://t.co/jbaemzHmsj

[Johannes Kopf @JPKopf]

You’re revealing our best secrets...

[Jia-Bin Huang @jbhuang0604]

How can I get my paper on the top?

Understand that arXiv is a "stack" data structure (first in last out, FILO)! Submit your paper RIGHT BEFORE THE DEADLINE will make your paper appear on the top! Probably the easiest way to improve your paper visibility.

[Johannes Kopf @JPKopf]

Wow, this is really cool! I didn’t know it’s a thing and people create so many of these. We’re kinda aiming at doing this in 3D -> So you can change the viewpoint interacively while it’s playing.

[randomoneh ⏸️ @randomoneh]

@JPKopf @jastarex @jbhuang0604 This would make some amazing panogifs.
https://t.co/abVeYb3SCY

[Johannes Kopf @JPKopf]

Robust-CVD works great for long videos as well. Such a fun tool to use!

https://t.co/pVuruyAIt9

[Johannes Kopf @JPKopf]

Hey! Algorithmically it’s relatively straightforward, and these methods will work well for 360. But there’s quite a bit of engineering involved. We’re looking into doing some of that work, though, because 360 *3D* videos will look absolutely amazing in VR!

[ArgentinaVR @ArgentinaVR2]

@JPKopf @jastarex @jbhuang0604 How are you? I have a question based in my singulars dreams, did you make a test on a 360 degree video, if not, it is possiblr to archirve a good result? Greetings from.argentina

[Johannes Kopf @JPKopf]

Now, just need to combine this with our recent space-time free-viewpoint video tech. Stay tuned!

[Johannes Kopf @JPKopf]

Our awesome new paper on *free-viewpoint* video from cell phone capture.

Space-time neural rendering with the powerful @wenqi_xian, @jbhuang0604, and @_ChangilKim!

Paper: https://t.co/ee3py34xmG
Website: https://t.co/8PoT5GmLMj

[Johannes Kopf @JPKopf]

We test the robustness by applying the method to ALL videos of existing video datasets.
So, no cherry picking! :)
Here’s all 90 DAVIS videos.

[Johannes Kopf @JPKopf]

Killer results, Aleks. This looks even improved compared to the last time I’ve seen it?

[Aleksander Holynski @holynski_]

Excited to show off our new project on single-image cinemagraphs. Our method automatically turns a _single image_ into a seamlessly looping video!

Website: https://t.co/nyySiXs9qk
Video: https://t.co/xGbjXF64TM

w/ Brian Curless, Steve Seitz, Rick Szeliski
More in thread! [1/5]

[Johannes Kopf @JPKopf]

Doesn’t look like a failure case to me :D

[Aleksander Holynski @holynski_]

And also some pretty cool failure cases -- if a class of objects aren't seen during training, but share similar textural properties to fluids...
[6/5]