Computer vision

Graduate student Alex Kachkine has developed a new technique that “uses AI-generated polymer films to physically restore damaged paintings in hours,” reports Benj Edwards for Ars Technica. “Kachkine's method works by printing a transparent ‘mask’ containing thousands of precisely color-matched regions that conservators can apply directly to an original artwork,” explains Edwards. “Unlike traditional restoration, which permanently alters the painting, these masks can reportedly be removed whenever needed. So it's a reversible process that does not permanently change a painting.” 

Guardian reporter Ian Sample highlights how graduate student Alex Kachkine has developed a new approach to restoring age-damaged artwork in hours. “The technique draws on artificial intelligence and other computer tools to create a digital reconstruction of the damaged painting,” explains Sample. “This is then printed on to a transparent polymer sheet that is carefully laid over the work.” 

Graduate student Alex Kachkine speaks with Nature reporter Amanda Heidt about his work developing a new restoration method for restoring damaged artwork. The method uses “digital tools to create a ‘mask’ of pigments that can be printed and varnished onto damaged paintings,” explains Heidt. The method “reduces both the cost and time associated with art restoration and could one day give new life to many of the paintings held in institutional collections — perhaps as many as 70% — that remain hidden from public view owing to damage.” 

Nature spotlights graduate student Alex Kachkine – an engineer, art collector and art conservator – on his quest to develop a new AI-powered, art restoration method, reports Geoff Marsh for Nature. “My hope is that conservators around the planet will be able to use these techniques to restore paintings that have never been seen by the general public,” says Kachkine. “Many institutions have paintings that arrived at them a century ago, have never been shown because they are so damaged and there are no resources to restore them. And hopefully this technique means we will be able to see more of those publicly.” 

Prof. Pulkit Agrawal speaks with Darian Woods and Geoff Brumfiel of NPR’s The Indicator from Planet Money about his work developing a simulator that can be used to train robots. “The power of simulation is that you can collect, you know, very large amounts of data,” explains Agrawal. “For example, in three hours', you know, worth of simulation, we can collect 100 days' worth of data.” 

Prof. Pulkit Agrawal speaks with NPR Short Wave host Regina Barber and science correspondent Geoff Brumfiel about his work developing a new technique that allows robots to train in simulations of scanned home environments. “The power of simulation is that we can collect very large amounts of data,” explains Agrawal. “For example, in three hours' worth of simulation, we can collect 100 days' worth of data.” 

Researchers at MIT have developed “Clio,” a new technique that “enables robots to make intuitive, task-relevant decisions,” reports Jennifer Kite-Powell for Forbes. The team’s new approach allows “a robot to quickly map a scene and identify the items they need to complete a given set of tasks,” writes Kite-Powell. 

Researchers at MIT have developed a new method that “enables robots to intuitively identify relevant areas of a scene based on specific tasks,” reports Baba Tamim for Interesting Engineering. “The tech adopts a distinctive strategy to make robots effective and efficient at sorting a cluttered environment, such as finding a specific brand of mustard on a messy kitchen counter,” explains Tamim. 

Writing for Fast Company, Moshe Tanach highlights how researchers from the MIT Lincoln Laboratory Supercomputing Center are developing new technologies to reduce AI energy costs, such as power-capping hardware and tools that can halt AI training. 

MIT researchers have improved upon the diffusion models used in AI image generation, reports Alok Jha for The Economist. Working with electrically charged particles, the team created “Poisson flow generative models,” which “generate images of equal or better quality than state-of-the-art diffusion models, while being less error-prone and requiring between ten and 20 times fewer computational steps,” Jha explains. 

Researchers at CSAIL have created three “libraries of abstraction” – a collection of abstractions within natural language that highlight the importance of everyday words in providing context and better reasoning for large language models, reports Darren Orf for Popular Mechanics. “The researchers focused on household tasks and command-based video games, and developed a language model that proposes abstractions from a dataset,” explains Orf. “When implemented with existing LLM platforms, such as GPT-4, AI actions like ‘placing chilled wine in a cabinet' or ‘craft a bed’ (in the Minecraft sense) saw a big increase in task accuracy at 59 to 89 percent, respectively.”

In a new study examining the potential impact of AI on jobs that employ computer vision, MIT researchers found, “a vast majority of jobs previously identified as vulnerable to AI are not economically beneficial for employers to automate at this time,” reports Catherine Thorbecke for CNN. “In many cases, humans are the more cost-effective way, and a more economically attractive way, to do work right now,” says Research Scientist Neil Thompson, director of the FutureTech Research Project at CSAIL. “What we’re seeing is that while there is a lot of potential for AI to replace tasks, it’s not going to happen immediately.”

A new working paper by MIT researchers finds that artificial intelligence is not currently a cost-effective replacement in jobs where computer vision is employed, reports Saritha Rai for Bloomberg. “Our study examines the usage of computer vision across the economy, examining its applicability to each occupation across nearly every industry and sector,” explains Research Scientist Neil Thompson, director of the FutureTech Research Project at CSAIL. “We show that there will be more automation in retail and healthcare, and less in areas like construction, mining or real estate.”

A new working paper by MIT researchers focuses on whether human work, including vision tasks, are worth replacing with AI computer vision, reports Jeremy Hsu for New Scientist. “There are lots of tasks that you can imagine AI applying to, but actually cost-wise you just wouldn’t want to do it,” says Research Scientist Neil Thompson, director of the FutureTech Research Project at CSAIL.

Researchers at MIT have released a new working paper that aims to quantify the severity and speed with which AI systems could replace human workers, reports Hiawatha Bray for The Boston Globe. The paper concluded that “it’s not enough for AI systems to be good at tasks not performed by people,” explains Bray. “The system must be good enough to justify the cost of installing it and redesigning the way a job is done.”