Rezultati pretraživanja
  1. 25. sij

    1. Draw shapes in , by hand 2. Run with , fingers crossed 🤞

  2. 21. sij

    Recently I put together a small dataset of Bentley's classic snowflake photos, and trained a model. Here I generated some shapes with Pts.js and ran them through the model. Initial results -- (I probably need to train it some more but it's so expensive! 😭)

  3. By the end of 2017 my efforts to improve resolution were obliterated by two major breakthroughs: in short succession first showed their highly realistic celebrities made with and followed up with shortly after.

    Prikaži ovu nit
  4. 19. pro 2019.

    Some generated snow crystals from GAN, based on Wilson Bentley's classic photos. Training is still in progress, slowly slowly. More to come soon!

    Prikaži ovu nit
  5. I personally think if this image is converted into segment ( how pix2pixhd works ) then i m sure var won’t make these types of errors. We need image to outline based concept here.

  6. Both models are shallow ResNets derived from . I first tried UNets, but there the models learned to cheat very quickly and just abused the first skip connection to pass the information almost uncompressed.

    Prikaži ovu nit
  7. 18. lip 2019.

    We have released our under the BSD license (It was under CC non-commercial license.) Please feel free to use it.

  8. Thx 🙏 :). (To complete the loop, this 👇 is based on , coauthored by , also coauthor on . & other coauthors are from ).

  9. 15. ožu 2019.

    Glad to see that our research works enable people to "generate realistic dance videos of NBA players for in-game entertainment." ,

    Prikaži ovu nit
  10. 1. ožu 2019.

    Some more developments in a series that extends work exhibited at 1/many

    Prikaži ovu nit
  11. 5. velj 2019.

    Some more initial results from a series that extends work exhibited at . Using streetview data, we trained a model to transform depthmap images to photographic images.

    Prikaži ovu nit
  12. Research at the lab | turning video games into interactive mode to question the value of designed pixels in future graphical productions | This is controlled with a body

    Prikaži ovu nit
  13. The principle is pretty simple: in a classic residual architecture you chain several residual blocks behind each other (in the default is 9 blocks), what I do in is to use a single block, but loop 9 times over it, feeding its output back into its input.

    Prikaži ovu nit
  14. I've created an experimental GAN architecture I call or "Recursive-Residual GAN" and I am pretty astonished that: - it works at all - how well it works across a pretty wide range of scales. - it is just 15% the size of a comparable model

    Portrait generated by RecuResGAN - replication of training example
    Portrait generated by RecuResGAN - replication of training example
    Portrait generated by RecuResGAN - replication of training example
    Portrait generated by RecuResGAN - replication of training example
    Prikaži ovu nit
  15. 7. stu 2018.
  16. Odgovor korisniku/ci

    Thanks! There are 5 different GANs involved which employ my own architecture that owes a lot to and .

  17. by "Synthesizing and manipulating 2048x1024 images with conditional GANs"

    Prikaži ovu nit
  18. 27. kol 2018.

    Hopping on the frame prediction train. Here's a feedback loop between 2 models, one trained to predict the next frame in a video, the other trained to predict the original frame from a version processed by the other model between 1 and 10 times.

    Prikaži ovu nit
  19. Odgovor korisniku/ci

    These are some snapshots from the training of my custom version of using on the Costică Acsinte archive.

  20. Indulging in : the delicious ResNet filling of in a coating of crunchy unet skip connections from classic. I have no idea if that combination will fly.

    Prikaži ovu nit

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.