new feature in photoshop CS5


Recommended Posts

Fake.

You can't possibly fill the white space around the panorama like that without know the rest of the image. No algorithm can find that the mountain slopes down on the right unless it has that info somewhere.

thats exacty what I thought. I think he just pressed ctrl+v to restore the image after the progress bar finished.

wtf, when did pc's become intelligent enough to even understand the concept of content in a photo. I think I skipped a few years somewhere along the line :p

from the description on youtube:

One of the biggest requests we get of Photoshop is to make adding, removing, moving or repairing items faster and more seamless. From retouching to completely reimagining an image, heres an early glimpse of what could happen in the future when you press the delete key. How might you use this new capability in your workflow?

"could" happen? I already thought it looked a bit too futuristic, let's see if and how well it works in CS 5 ;)

The photoshop 'Spot Healing' tool works very well, so why cant it work on a larger scale?

I would say in this day and age, its most likely true. It would ruin their credability to advertise something so large as this and not follow through.

Plus adobe are not known for joking around with publicity.

Based on how well the healing brush works, this doesn't really seem impossible to me.

And being content aware isn't as hard as some people believe. It's all about analyzing the photo finding edges ridges and patterns and extending them.

As for filling out the panorama, at no point did he say the final photo looked like the real place. because it most likely didn't. It's just how photoshop guesstimated it looked.

Fake.

Really? Adobe would fake a demonstration of a product they're about to release? Really?

You can't possibly fill the white space around the panorama like that without know the rest of the image. No algorithm can find that the mountain slopes down on the right unless it has that info somewhere.

No, but it can make something up. That's all it does. It makes something up, something that more or less fits into the scene. This is the same thing you'd do by hand. The goal is to make something that looks good, not recreate the actual landscape out of thin air. Do you really not understand this?

Now you see why The Gimp will never compete :p

Sorry but, the gimp has had a plugin of this before CS5. Its called the Resynthesize plugin, and in some cases does a better job. Heres a comparison.

http://o3.tumblr.com/post/470608946/photoshops-caf-content-aware-fill-unbelievable

The gimp version came up with a better result on the Desert road picture.

This topic is now closed to further replies.
  • Recently Browsing   0 members

    • No registered users viewing this page.
  • Posts

    • Google Gemini co-lead Noam Shazeer is leaving for OpenAI by Pradeep Viswanathan Noam Shazeer is best known as one of the co-authors of the 2017 “Attention Is All You Need” paper, which introduced the Transformer architecture that now powers most large language models. He also worked on several major Google AI projects, including LaMDA, before leaving the company in 2021 to co-found Character.AI. He also authored the Sparsely-gated Mixture of Experts (2016) paper, which is popular among the AI community. After falling behind OpenAI and Anthropic a couple of years ago, Google brought Shazeer back in 2024 as part of a major deal with Character.AI. Through this deal, along with Noam, several other researchers returned to Google DeepMind. More recently, he was a vice president of engineering at Google and a technical co-lead for Gemini. Today, Noam Shazeer announced on X that he is leaving Google and joining OpenAI. In his post, Shazeer said it was a difficult decision to move on, adding that he was proud of the Google team and what it had built together. OpenAI CEO Sam Altman welcomed the move with a post of his own, saying Shazeer was one of the people he had most wanted to work with since OpenAI’s early days. Google has made strong progress with Gemini over the past year, closing the gap with OpenAI in several areas. But losing Noam Shazeer is a major talent setback for them, especially after bringing him back less than two years ago by spending a fortune. For OpenAI, the hire adds one of the industry’s most experienced language model researchers to a team that is already pushing ahead with ChatGPT, Codex, and its next generation of frontier models.
    • I'm lost too... what did you mean by your first comment then?
    • Couple years ago I got a brand new 4TB Samsung 990 Pro for $250 during Black Friday
    • Thanks
  • Recent Achievements

    • Week One Done
      Classifyskilleducation earned a badge
      Week One Done
    • One Month Later
      eurospharma62 earned a badge
      One Month Later
    • Week One Done
      With What earned a badge
      Week One Done
    • Week One Done
      Harris Gilbert earned a badge
      Week One Done
    • One Month Later
      Vincian earned a badge
      One Month Later
  • Popular Contributors

    1. 1
      +primortal
      542
    2. 2
      +Edouard
      171
    3. 3
      PsYcHoKiLLa
      85
    4. 4
      ATLien_0
      64
    5. 5
      neufuse
      64
  • Tell a friend

    Love Neowin? Tell a friend!