Experience Real-Time 4K Image Transformation with Laplacian Pyramid

Поділитися
Вставка
  • Опубліковано 5 січ 2025

КОМЕНТАРІ • 23

  • @WhatsAI
    @WhatsAI  3 роки тому +4

    References:
    ►Read the full article: www.louisbouchard.ai/4k-image-translation-in-real-time/
    ►Liang, Jie and Zeng, Hui and Zhang, Lei, (2021), "High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network", export.arxiv.org/pdf/2105.09188.pdf
    ►Code: github.com/csjliang/LPTN

  • @esperamea3095
    @esperamea3095 3 роки тому +7

    it is really impressive ,thank you for making us discover this paper

    • @WhatsAI
      @WhatsAI  3 роки тому +1

      I agree, it's clever and very impressive! It is my pleasure, glad to be able to share these amazing papers with you! :)

  • @AICoffeeBreak
    @AICoffeeBreak 3 роки тому +1

    Great video, keep going! 👏

    • @WhatsAI
      @WhatsAI  3 роки тому

      Thank you ☺️

  • @letsburn00
    @letsburn00 3 роки тому +1

    I'm a bit of a newbie at ML. To confirm, it looks like it has a simplifying algo, effectively convolutions as an upscaling method.
    They downscaled massively, do the image changes, then use the previously developed convolutional maps to reupscale the image.

    • @WhatsAI
      @WhatsAI  3 роки тому +1

      Exactly! And only the downscaled image is sent into the typical encoder-decoder architecture we use in GANs instead of the whole image! Which is why it is so much faster.

    • @NicoRichter42
      @NicoRichter42 3 роки тому +1

      @@WhatsAI I think calling it downscaling instead of low frequency would have made it easier to understand for themathematically less inclined 😉. Thanks for making the video though,this is a brilliant approach indeed!

    • @WhatsAI
      @WhatsAI  3 роки тому

      Thank you, noted! I tried to introduce this high-low frequency nuance as it's the terminology they used in the paper and I like seeing it this way more haha! But I agree, I should've made the comparison more clear!

  • @M_Jema4703
    @M_Jema4703 3 роки тому +1

    Impressive!👌 Love it😍
    Gonna use it in my personal project😋

    • @WhatsAI
      @WhatsAI  3 роки тому

      Amazing! Please let me know your progress and what you do with it!

    • @M_Jema4703
      @M_Jema4703 3 роки тому +1

      @@WhatsAI a year or so ago I started working on a project called lane area segmentation. Initially I trained model on around 10k images and images were captured by dashcam. The trained model really did a great job segmenting lane area in regular sunny day and more or less shadow as well. But it failed terribly in weather like situations. Now that we have a new approach that is faster I'm planning to use it as augmentation for robustness. I hope it will work.

    • @WhatsAI
      @WhatsAI  3 роки тому +1

      Oh awesome application!

    • @M_Jema4703
      @M_Jema4703 3 роки тому

      Thanks Louis.

  • @AIhyp
    @AIhyp 3 роки тому +2

    Impressive like it!!!

  • @yixinren8707
    @yixinren8707 2 роки тому +1

    This method is suitable for photorealistic neural style transfer, because it only considered the color and illumination, and I dont think it works for non-photorealistic NST.😅

    • @WhatsAI
      @WhatsAI  2 роки тому

      I think so too!

  • @aguilarrojasoctavio4402
    @aguilarrojasoctavio4402 3 роки тому +1

    The future is awating us

  • @mostechroom9780
    @mostechroom9780 3 роки тому +1

    First comment ? Love your videos

    • @WhatsAI
      @WhatsAI  3 роки тому

      Thank you so much! Glad that you are the first comment then! ;)

  • @danielsalinas602
    @danielsalinas602 3 роки тому +1

    👏👏👏👏👏

  • @mostechroom9780
    @mostechroom9780 3 роки тому +1

    Do you implement the papers that you talk about in your videos? and if so, how difficult is it to implement them

    • @WhatsAI
      @WhatsAI  3 роки тому

      I do implement some of them and not others, it depends! Sometimes there's just no code given. For this one, the GitHub repo is very clear and easy to follow + implement! Just follow their steps one by one :)