【这些”AI+3D打印“复制的画作,你认得出来吗?】

【这些”AI+3D打印“复制的画作,你认得出来吗?】麻省理工的研究人员开发了一款“RePaint”的AI软件,用深度学习在三维层面复原艺术画作。他们配套使用了一种”颜色调节“特殊技术,用3D打印机将10种不透明的油墨堆叠在非常薄的层中,这种技术复原的艺术品色调,远比二维像素手段要繁复、广泛得多。

Can YOU spot the difference? Art fanatics may one day be able to 3D print their own version of a priceless masterpiece

  • Physical reproductions were made the size of a business card to minimise costs 
  • A piece of software called 'RePaint' combines 3D painting with AI to make them 
  • It allows for the production of more colours than  traditional 2D printing 

If you've ever wanted to get your hands on the Mona Lisa, you may just be in luck.

For researchers have found a way for art fanatics to create  their own version of a priceless masterpiece, through a combination of AI and 3D printing.

The replicas have been made by researchers from the Massachusetts Institute of Technology (MIT) using a piece of software called 'RePaint'.

Researchers have found a way for art fanatics to create their own version of a priceless masterpiece, through a combination of AI and 3D printing 

The replicas have been made by researchers from the Massachusetts Institute of Technology (MIT) using a piece of software called 'RePaint' (pictured)

Despite the progress so far, the team says they have a few improvements to make before they can whip up a dazzling dupe of 'Starry Night.'

'If you just reproduce the colour of a painting as it looks in the gallery, it might look different in your home,' says Changil Kim, one of the researchers from MIT that published a paper on the system, which will be presented in December.

'Our system works under any lighting condition, which shows a far greater colour reproduction capability than almost any other previous work.'

A number of oil paintings were created by an artist for the project and they were then recreated using RePaint.

Researchers claim that RePaint was more than four times more accurate than state-of-the-art physical models at creating the exact colour shades for different artworks.

The physical reproductions were made the size of a business card to minimise costs as the project is currently still expensive.

MIT researchers used a special technique called 'colour-contoning', which involves using a 3-D printer and 10 different transparent inks stacked in very thin layers.

This allows for a wider range of colours and hues to be created than with traditional 2D printing.

A number of oil paintings were created by an artist for the project and they were then recreated using RePaint 

Researchers claim that RePaint was more than four times more accurate than state-of-the-art physical models at creating the exact colour shades for different artworks

MIT researchers have trained a deep learning model to predict the optimal stack of different inks. It was then fed images of paintings, and used the model to determine what colours should be used in what particular areas for specific paintings 

According to mechanical engineer Mike Foshey, they couldn't completely reproduce certain colours like cobalt blue due to a limited ink library 

They combined their method with a decades-old technique called 'halftoning', where an image is created by tons of little ink dots, rather than continuous tones. Combining these, the team says, better captured the nuances of the colours.

The team trained a deep learning model to predict the optimal stack of different inks.

It was then fed images of paintings, and used the model to determine what colours should be used in what particular areas for specific paintings.

According to mechanical engineer Mike Foshey, they couldn't completely reproduce certain colours like cobalt blue due to a limited ink library.

https://www.dailymail.co.uk/sciencetech/article-6439091/Damaged-artworks-restored-using-combination-3D-printing-AI-say-MIT-researchers.html


Comments are closed.



无觅相关文章插件