Dan Rosenbaum retweetledi
Cat's out of the bag (and the cat is actually a unicorn 🦄)!
Come do cool research with us in sunny Barcelona 🌞fundamental.tech/research
English
Dan Rosenbaum
102 posts
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: osmosis-diffusion.github.io
English
Dan Rosenbaum retweetledi
youtube.com/watch?v=7rTFuV…
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
YouTube
English
Dan Rosenbaum retweetledi
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
Vancouver, British Columbia 🇨🇦 English
Dan Rosenbaum retweetledi
Vancouver, British Columbia 🇨🇦 English
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 youtu.be/oRMvTBBARKE
English
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. 📝arxiv.org/abs/2302.03130
English
Dan Rosenbaum retweetledi
Functa is now open-sourced!💻 Hope it's useful to those of us exploring INRs/Neural fields 😀
github.com/deepmind/functa
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 📝arxiv.org/abs/2201.12204 w/ @emidup @arkitus @DaniloJRezende @danrsm, to appear in ICML22
English
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 📝arxiv.org/abs/2201.12204 w/ @emidup @arkitus @DaniloJRezende @danrsm, to appear in ICML22
English
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 📝arxiv.org/abs/2201.12204 w/ @emidup @arkitus @DaniloJRezende @danrsm, to appear in ICML22
English
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! mlsb.io
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: arxiv.org/abs/2106.14108. @danrsm, @GarneloMarta, @MichaelZielins, @JonasAAdler, @arkitus, @CarlDoersch, @pushmeet
English
Dan Rosenbaum retweetledi
@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' arxiv.org/abs/2106.14108.
English
Dan Rosenbaum retweetledi
Heartbroken to learn of the untimely passing of Tali Tishby. A profound thinker and a gentle and fine human: a great loss. en.m.wikipedia.org/wiki/Naftali_T…
English
Dan Rosenbaum retweetledi
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
arxiv.org/abs/2106.12052
(1/8)
GIF
English
Dan Rosenbaum retweetledi
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.
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: arxiv.org/abs/2106.14108. @danrsm, @GarneloMarta, @MichaelZielins, @JonasAAdler, @arkitus, @CarlDoersch, @pushmeet
English
Dan Rosenbaum retweetledi
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
arxiv.org/abs/2106.14108.
English
Dan Rosenbaum retweetledi
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!
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: arxiv.org/abs/2106.14108. @danrsm, @GarneloMarta, @MichaelZielins, @JonasAAdler, @arkitus, @CarlDoersch, @pushmeet
English
Modelling protein structure dynamics with inverse graphics: from cryo-EM images to a distribution of atom coordinates arxiv.org/abs/2106.14108
@JonasAAdler, @ORonneberger, @GarneloMarta, @MichaelZielins, @arkitus, @CarlDoersch, @pushmeet
English
Dan Rosenbaum retweetledi
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: arxiv.org/abs/2106.14108.
@danrsm, @GarneloMarta, @MichaelZielins, @JonasAAdler, @arkitus, @CarlDoersch, @pushmeet
English
Dan Rosenbaum retweetledi
By framing generative modeling as learning distributions of functions, we build models that act entirely on continuous spaces, independently of data resolution 🌿
📄 Paper: arxiv.org/abs/2102.04776
💻 Code: git.io/JG2KV
with @yeewhye @ArnaudDoucet1
GIF
English