Closed-Form Factorization of Latent Semantics in GANs
— AK (@ak92501) July 15, 2020
pdf: https://t.co/pYda24esEJ
abs: https://t.co/TTx4gwm5Xl pic.twitter.com/7YuVWnuquW
Closed-Form Factorization of Latent Semantics in GANs
— AK (@ak92501) July 15, 2020
pdf: https://t.co/pYda24esEJ
abs: https://t.co/TTx4gwm5Xl pic.twitter.com/7YuVWnuquW
It's been a year since we last used GANs.
— Jason Antic (@citnaj) June 16, 2020
You may have been lead to believe that GANs are -the- way to get realistic results but believe me, there's actually better ways IMHO. I can't tell you exactly what we're doing now but I can tell you this:
2/
Big GANs Are Watching You: Towards Unsupervised Object Segmentation with Off-the-Shelf Generative Models
— roadrunner01 (@ak92501) June 11, 2020
pdf: https://t.co/0buscthKLU
abs: https://t.co/coBhnX0xZA
github: https://t.co/hcxZFcqXCp pic.twitter.com/i0ii4p6Nl7
Latent Adversarial Generator Code is Out!
— David Berthelot (@D_Berthelot_ML) May 21, 2020
Code: https://t.co/2XmNyIcEVv
Arxiv: https://t.co/a8HqVpAl2r@docmilanfar @goodfellow_ian pic.twitter.com/O64yKLJMQ7
Adversarial Colorization Of Icons Based On Structure And
— roadrunner01 (@ak92501) May 18, 2020
Color Conditions
pdf: https://t.co/6tIoJZiXye
abs: https://t.co/2LakM2d1bk
github: https://t.co/hV7v3wlzvU pic.twitter.com/OQ550tvGgp
PixelMe: Convert your photo into Pixel Arthttps://t.co/ZV5BmUjc3nhttps://t.co/mSipIrIUiW pic.twitter.com/tf0hzogkfi
— hardmaru (@hardmaru) May 5, 2020
GANSpace: Discovering Interpretable GAN Controls
— roadrunner01 (@ak92501) April 7, 2020
pdf: https://t.co/tH7vtx01WI
abs: https://t.co/ifbCng1T5T
video: https://t.co/xVbOsFNNu1
github: https://t.co/W4PJQZSxqv pic.twitter.com/OsRIpdEpjz
Mimicry: a lightweight #PyTorch library aimed towards the reproducibility of GAN research
— Alexandr Kalinin (@alxndrkalinin) April 6, 2020
- standardized implementations of popular GANs
- baseline scores of GANs for comparison
- a framework for GAN training boilerplate codehttps://t.co/qPBkOesJcV pic.twitter.com/663dzlIJLq
"Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) input image is challenging due to missing details in under-/over-exposed regions caused by quantization and saturation of camera sensors."
— 👩💻 DynamicWebPaige @ 127.0.0.1 🏠 (@DynamicWebPaige) April 5, 2020
These are beautiful results! 🖼️✨https://t.co/dUfYZbQank pic.twitter.com/NdM2d9hBha
A GAN for House Plans
— hardmaru (@hardmaru) April 1, 2020
The model can generate realistic floor plan layouts based on a relational graph that encodes the architectural constraint (e.g., the number and types of rooms with their spatial adjacency).
I guess we can see this in AutoCAD soon?https://t.co/ODXS3QHkKX https://t.co/LrdFq6KS6e pic.twitter.com/Hpxk3vZUVu
"Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling" This technique can dramatically improve existing trained GANs, by re-interpreting them as an easy-to-sample-from energy based model in the latent space. https://t.co/f9dlYyJJPB
— Jascha (@jaschasd) March 28, 2020
Improved Techniques for Training Single-Image GANs
— roadrunner01 (@ak92501) March 25, 2020
github: https://t.co/NtTbBAPN7G
blog: https://t.co/zyhjO6Ht7n pic.twitter.com/HgaWOPQIPV