MIT graduate student reduced painting restoration from 230 to 3.5 hours
MIT graduate student Alex Kachkin developed a cool method for painting restoration using artificial intelligence. Reducing work time from many months to several hours. As a demonstration, he restored a work by an unknown Dutch master of the 15th century that had seriously suffered from time.
The restoration process included several technological stages. First, algorithms created a digital copy, filling small cracks based on analysis of neighboring colors and restoring ornaments. To preserve historical authenticity, the researcher refused generative neural networks. Instead, he supplemented lost elements like faces with fragments from other works by the artist, using traditional graphic editors. The final step is truly genius. The restored digital elements were printed on ultra-thin transparent polymer and overlaid on the original. This film is invisible to the human eye but can be easily removed without the slightest harm to the painting. The entire application process took only 3.5 hours, while traditional restoration would require more than 230 hours of painstaking work. This technology will open access to many paintings around the world. Because it turns out that 70% of all museum paintings are not displayed. Due to damage.
Autor: AIvengo
For 5 years I have been working with machine learning and artificial intelligence. And this field never ceases to amaze, inspire and interest me.
10 million interactions with fake celebrity bots at MetaMark Zuckerberg's company created dozens of chatbots using the identities of Taylor Swift, Scarlett Johansson and other stars without their permission. These virtual doubles even generated photorealistic images of a delicate nature. Reuters reported on the scale of the scandal after weeks of investigation.
10 million interactions with fake celebrity bots at MetaMark Zuckerberg's company created dozens of chatbots using the identities of Taylor Swift, Scarlett Johansson and other stars without their permission. These virtual doubles even generated photorealistic images of a delicate nature. Reuters reported on the scale of the scandal after weeks of investigation.
AI agent race: DeepSeek vs OpenAI and Chinese ManusDeepSeek is preparing its AI agent that will go beyond familiar chatbots. Bloomberg reveals details of the technology race where the Chinese startup wants to catch up with American OpenAI and local competitor Manus. Reports say company founder Liang Wenfeng personally controls the project and demands results by year-end.
6 Cialdini principles against ChatGPT security systemsChatGPT is susceptible to flattery and executes forbidden requests after psychological manipulations. This was discovered by University of Pennsylvania scientists. When they hacked GPT-4o Mini using principles from a book on persuasion psychology. Artificial intelligence proved vulnerable to human tricks.
