I always feel frustrated at taking photos through fences or windows (e.g., when taking my kids to the zoo). Check out our #CVPR2020 work on "learning to see through the obstructions"
Paper: https://t.co/IfKfp9n5nf
Code: https://t.co/TAphDNXssQ
Colab: https://t.co/OM8UjTkYuF
@flattencurve We also have a few things to confirm with you: in a couple paragraphs, we changed the text related to the US healthcare system to our local information
@flattencurve Hi, how can I get access to the tool? We have the text translated and proof-read by a team of volunteers and experts, and we want to publish it asap
Now it works. Let's spatially explore the 2D images!
Thanks for tips, @jonathanfly!
And Special Kudos to @simon_niklaus - 3D Ken Burns model is his great work!
Here is what happens if you exaggerate this model. And it's amazing.
For one of our Friday talks, Paul did a lecture on color, and we were so excited about it that we went a little overboard and created an entire app out of it.
It starts by explaining how color works, and ends with a palette making challenge 🤹♂️ https://t.co/4Qlwvrz3WI
StyleGAN 2: Mostly We Got Rid of The Blobs
Also: No 'phase artifacts' (I hadn't noticed them but obvious in retrospect), easier-to-navigate latent spaces mean better encoding, and ~25% more efficient.
pdf: https://t.co/aryV2r8JbU
code (coming-later): https://t.co/fB8GLTYC8G
Just got refused a Canadian visa I needed to present my poster at #cogsci2019. I believe that not everybody fully realizes how much visa issues hurt diversity in academia. So here goes my thread on the topic.
Successfully replicated NVIDIA's 512x512 labels-to-landscapes model (GauGAN) for use with SPADE. The model can be downloaded from https://t.co/E7RCwRJrlX
It will also be available on @runwayml shortly. Here it is in action!
VQVAE-2 finally out!
Powerful autoregressive models in a hierarchical compressed latent space. No modes were collapsed in the creation of these samples ;)
Arixv: https://t.co/nQH5dzQhib
With @catamorphist and @vinyals
More samples and details 👇 [thread]