Dan Rosenbaum

[Marta Garnelo @GarneloMarta]

Cat's out of the bag (and the cat is actually a unicorn 🦄)!

Come do cool research with us in sunny Barcelona 🌞https://t.co/5ylAgjpNQt

[Dan Rosenbaum @danrsm]

Ever wondered how underwater scenes would look like without water?🪸🤿
Come check our work at #ECCV24 in Milan tomorrow.
Osmosis: RGBD Diffusion Prior for Underwater Image Restoration. 
Opher Bar Nathan, Deborah Levy, @TreibitzL. 
Poster#237 16:30
Code: https://t.co/1KB1HajLbo

[Treibitz Marine Imaging Lab @TreibitzL]

https://t.co/DkIBbdzo5g
Sea Thru #NeRFs enable us to model the underwater environment and as a result remove the water and expose how the scene looks like without water. Come see our poster (number 6) Tue AM in #CVPR2023.
@dakkaynak
@SimonKorman
@danrsm

[Treibitz Marine Imaging Lab @TreibitzL]

Come see our poster (number 6)- we use a novel underwater #nerf formulation to remove the water and restore the scenes #CVPR2023 @dakkaynak @SimonKorman @danrsm

[Treibitz Marine Imaging Lab @TreibitzL]

If you missed our presentation today in the #NeRF workshop, come to our poster Tuesday AM #CVPR23

[Dan Rosenbaum @danrsm]

NeRF goes underwater! 🤿

[Treibitz Marine Imaging Lab @TreibitzL]

How do you synthesize novel views underwater? Happy to share results from our new #CVPR2023 paper: "SeaThru-NeRF: Neural Radiance Fields in Scattering Media", Deborah Levy, Amit Peleg , Naama Pearl, Dan Roesnbaum, Derya Akkaynak, Simon Korman, Tali Treibitz.
@dakkaynak @SimonKorman @danrsm @CVPR #NeRFs #nerf #3dmodeling #Photogrammetry #ocean #oceans

https://t.co/DwNDDhBBd8

[Dan Rosenbaum @danrsm]

Scaling up functa

[Hyunjik Kim @hyunjik11]

Previously we had introduced *functa*, a framework for representing data as neural functions (aka neural fields, INRs) and doing deep learning on them.
In our recent work *spatial functa* we show how to scale up the approach to ImageNet-1k 256x256.
📝https://t.co/Gw4Fu37V4W

[Hyunjik Kim @hyunjik11]

Functa is now open-sourced!💻 Hope it's useful to those of us exploring INRs/Neural fields 😀
https://t.co/tdf4OTar8y

[Dan Rosenbaum @danrsm]

If you're at #ICML2022 come see the talk and poster today of our work on treating data points as functions
w/ @emidup @hyunjik11 @arkitus @DaniloJRezende

[Hyunjik Kim @hyunjik11]

Ever wondered why deep learning is always done on array data?🤔 Happy to announce our work:

From data to functa: Your data point is a function and you can treat it like one

📝https://t.co/cgudChXTI1 w/ @emidup @arkitus @DaniloJRezende @danrsm, to appear in ICML22

[Dan Rosenbaum @danrsm]

Check out our new 💃functa🕺work!
How can function representation lead to psychedelic cars?

w/@hyunjik11 @emidup @arkitus @DaniloJRezende

[Hyunjik Kim @hyunjik11]

Ever wondered why deep learning is always done on array data?🤔 Happy to announce our work:

From data to functa: Your data point is a function and you can treat it like one

📝https://t.co/cgudChXTI1 w/ @emidup @arkitus @DaniloJRezende @danrsm, to appear in ICML22

[Dan Rosenbaum @danrsm]

If you're interested in dynamic protein structure, cryo-EM data, and/or inverse graphics approaches, come see our talk and poster today at the MLSB workshop at NeurIPS 3:30PM GMT! https://t.co/IyQqeEP7U0

[Olaf Ronneberger @ORonneberger]

Proteins are not static bricks! Feasibility study to infer a continuous distribution of all states using an end-to-end model from Cryo-EM images to atom coordinates: https://t.co/CgoBlyr1Ao.
@danrsm, @GarneloMarta, @MichaelZielins, @JonasAAdler, @arkitus, @CarlDoersch, @pushmeet

[Stephanie Wankowicz @stephanie_mul]

@fraser_lab and I, along with many colleagues (including @irisdyoung), held a journal club on the exciting new @DeepMind paper 'Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs' https://t.co/sphuBJ1ehQ.

[Adrienne Fairhall @alfairhall]

Heartbroken to learn of the untimely passing of Tali Tishby. A profound thinker and a gentle and fine human: a great loss. https://t.co/7lfghxZxtn

[Lior Yariv @YarivLior]

Excited to share "Volume Rendering of Neural Implicit Surfaces" (VolSDF): a volume rendering framework for implicit neural surfaces, allowing to learn high fidelity geometry from a sparse set of input images.

with @thoma_gu @yoni_kasten @lipmanya

https://t.co/WlUcVzRw0y
(1/8)

[Carl Doersch @CarlDoersch]

Cryo-EM: fascinating open vision problem I wouldn't even know about without this collab. Images are so noisy that each one gives only a little info on the 3D shape. We need Bayesian inference in generative models to explain all images w/ a physically-plausible state distribution.

[Kevin K. Yang 楊凱筌 @KevinKaichuang]

Infer a continuous distribution over atom coordinates from cryo-EM images using a VAE. The VAE decoder includes a model of how atoms generate images!

@danrsm @GarneloMarta @MichaelZielins @JonasAAdler @arkitus @CarlDoersch @ORonneberger
@pushmeet

https://t.co/iY447XtcNV.

[Ali Eslami @arkitus]

Interested in generative models, 3D computer vision or inverse graphics?

We use ideas and techniques from these fields to show the possibility of imaging very small objects (e.g. proteins) more effectively.

In this setting we cannot fall back to supervised learning!

[Dan Rosenbaum @danrsm]

Modelling protein structure dynamics with inverse graphics: from cryo-EM images to a distribution of atom coordinates https://t.co/cAj6vt6I21
@JonasAAdler, @ORonneberger, @GarneloMarta, @MichaelZielins, @arkitus, @CarlDoersch, @pushmeet

[Olaf Ronneberger @ORonneberger]

Proteins are not static bricks! Feasibility study to infer a continuous distribution of all states using an end-to-end model from Cryo-EM images to atom coordinates: https://t.co/CgoBlyr1Ao.
@danrsm, @GarneloMarta, @MichaelZielins, @JonasAAdler, @arkitus, @CarlDoersch, @pushmeet

[Emilien Dupont @emidup]

By framing generative modeling as learning distributions of functions, we build models that act entirely on continuous spaces, independently of data resolution 🌿

📄 Paper: https://t.co/mNMf0du4mU
💻 Code: https://t.co/NdfMXONTCU

with @yeewhye @ArnaudDoucet1