https://xitter.gq/t.co/uzWGOKimdr
Joined May 2014
- Tweets63
- Following189
- Followers62
- Likes187
Pinned Tweet
Our paper "Generalizable Patch-Based Neural Rendering" was accepted as an oral at #ECCV2022.
Joint work with @_machc, Leonid Sigal and @kiamada.
Project Page: mohammedsuhail.net/gen_patch…
1/2🧵
We propose a method that can render an unseen scene from just patches sampled from the scene. At the core of our model is a three-transformer network that leverages epipolar geometry along with a canonicalized positional encoding that improves generalization capability.
2/2🧵
3
6
Suhail Mohammed retweeted
Generalizable Patch-Based Neural Rendering
abs: arxiv.org/abs/2207.10662
project page: mohammedsuhail.net/gen_patch…
Happy to announce that our Light Field Neural Rendering paper was among the 33 best paper finalists at #CVPR2022. Come see our talk today 1:30pm at the Great Hall A-D and poster #33.
youtu.be/D9w8mFDvHsQ
light-field-neural-rendering…
Excited to share our new paper "Light Field Neural Rendering" accepted for an oral at #CVPR2022!
Joint work with @_machc, Leonid Sigal and @kiamada.
Camera-ready: arxiv.org/abs/2112.09687
Code and results are available on the project page: light-field-neural-rendering…
1/n🧵
Suhail Mohammed retweeted
Patch extraction is a fundamental operation in deep learning, especially for computer vision.
By the end of this thread, you’ll know how to implement an efficient vectorized patch extractor (no for loops) in a few lines of code and learn about memory allocation in numpy.
1/n
Suhail Mohammed retweeted
We're very happy to publish a first version of the digital "Physics-based Deep Learning" book! Its central goal is to give a thorough, hands-on introduction to deep learning for physical systems. From simple physical losses to full hybrid solvers. physicsbaseddeeplearning.org…
Suhail Mohammed retweeted
Together with @joanbruna @PetarV_93 @TacoCohen we will be teaching a course on #geometricdeeplearning in the @AIMS_Next #AMMI program. The course is based on our protobook geometricdeeplearning.com/
Thanks @Moustapha_6C Teta Bahunde @panfordkobby for this opportunity
Suhail Mohammed retweeted
#GNNs are related to PDEs governing information diffusion on graphs. In a new paper with @b_p_chamberlain James Rowbottom @migorinova @stefan_webb @emaros96 we study a new class of Neural Graph Diffusion PDEs
Blog post: bit.ly/3gUOEL8
Paper: arxiv.org/abs/2106.10934
Suhail Mohammed retweeted
Proud to share our 150-page "proto-book" with @mmbronstein @joanbruna @TacoCohen on geometric DL! Through the lens of symmetries and invariances, we attempt to distill "all you need to build the architectures that are all you need".
geometricdeeplearning.com/
More info below! 🧵
Suhail Mohammed retweeted
I'm excited to announce in partnership with the @NVIDIA Deep Learning Institute that the Graphics Codex is now a free online computer graphics rendering and ray tracing textbook at
graphicscodex.courses.nvidia…
The programming projects run everywhere and are accelerated on RTX GPUs.
Suhail Mohammed retweeted
Ever wondered why variational inference + natural gradients + neural networks might be a good idea? Are you curious to follow the details of the mathematical derivations? I wrote a blog post on the new @CambridgeMLG blog: mlg-blog.com/2021/04/13/ngvi… 1/3
Suhail Mohammed retweeted
Today our lab is launching 🚀 invariances.org which will feature a series of tutorials (text 📜 +videos 📺) relating G-invariances, (graph) representation learning, extrapolation, and causality
Suhail Mohammed retweeted
Immersive Light Field Video with a Layered Mesh Representation
augmentedperception.github.i…
Suhail Mohammed retweeted
Episode 18 of The Thesis Review:
Eero Simoncelli, "Distributed Representation & Analysis of Visual Motion"
We discuss his PhD work on optical flow, Bayesian inference and the brain, and ideas from his PhD that influence his thinking today.
soundcloud.com/thesis-review…
Suhail Mohammed retweeted
Great question! Check out the tutorial.
Web: srush.github.io/dex-lang/tut…
Code: github.com/google-research/d…
Suhail Mohammed retweeted
While preparing material for my lectures, came across @RogerGrosse ‘s awesome course on training dynamics of neural networks: cs.toronto.edu/~rgrosse/cour…
The readings (links to NNTD Chapter X in the page) are highly recommended!
Suhail Mohammed retweeted
My main talks on Graph Neural Networks in 2020
1. Introduction to GNNs
youtube.com/watch?v=Iiv9R6Bj…
2. Recent developments in GNNs
youtube.com/watch?v=M60huxIv…
3. Benchmarking GNNs
youtube.com/watch?v=tuChBSo8…
Hope they can be useful.
Happy new year to everyone !
