Timur Bagautdinov

1/6 Introducing SDI or Score Distillation via Reparametrized DDIM, a new approach for 3D generation using diffusion models that brings 3D generation quality closer to that of 2D! Joint with @ocariz__ @KGreenewald @vitorguizilini @psycharo @vincesitzmann @JustinMSolomon

At Connect, we shared a look at what we’re calling Instant Codec Avatars—photorealistic representations of yourself created from some scans from your phone + a few hours of processing time. Dive into our Reality Labs Research updates on Tech at Meta: tech.fb.com/ar-vr/2022/10/…

Check out our latest work on drivable avatars: DVA #SIGGRAPH2022 !

1/n Some really mind blowing technological advancements got lost in the excitement over the Meta name change yesterday. Let's start with lifelike avatars - this is an animated avatar not a video recording...

Great work at @CVPR from colleagues from @nc_shape and @EPFL on modulating the correlation between dropout patterns to get a model between dropout and ensemble of independent models. nikitadurasov.github.io/projects/masks…

Excited about volumetric avatars and NeRF? 😆 Compositional NeRF for high-quality face rendering has been accepted to CVPR 2021 as an Oral paper. arxiv.org/pdf/2012.09955…

Our upcoming #CVPR2021 paper on efficient uncertainty estimation. tldr: a drop-in replacement for mc-dropout that works (almost) as good as ensembles 😀

In practice, standard "deep ensembles" of independently trained models provides a relatively compelling Bayesian model average. This point is often overlooked because we are used to viewing Bayesian methods as sampling from some (approximate) posterior... 1/10

Check out our #NeurIPS2020 spotlight on differentiable iso-surface extraction tomorrow at 10:00 EST neurips.cc/virtual/2020/p… w @FuaPv

The bike optimized with our deep-learning aerodynamic simulation models was used to beat the world speed record in the women category and the European speed record in the men category! @nc_shape @EPFL_en @Idiap_ch #DeepLearning neuralconcept.com/2019/09/19/neu…

@ntvru хаха офигенно

@ChrisChoy208 We can, but the issue always remains how to efficiently compute the neighbours. I think in this context permutohedral essentially acts as a particular way to hash the inputs. An alternative would be to do sampling or something like locality sensitive hashing?

I did some #animation using the #edges2cats applet affinelayer.com/pixsrv/index.h…

Гусь у моря цитирует Иосифа Бродского arzamas.academy/results/970

By my calculations, the ML singularity will arrive around 2048.

Whatever idea you started working on last week, a few other teams have probably been working on it for a month and are about to publish.

List of #cvpr2016 papers with code made available online tensortalk.com/?cat=conferenc…

We’ve just released OpenAI Requests for Research, a living collection of deep learning research problems. openai.com/requests-for-r…

Robots not only move, but move with social etiquette! Am excited by our Jackrabbot! @StanfordCVGL @techreview goo.gl/OGwd9B

Видео первого пуска ракеты космического назначения «Союз-2.1а» с космодрома #Восточный!