Researchers at Tencent developed the GFP-GAN algorithm to repair corrupted images and low-resolution portraits. PetaPixel writes about it.

The technology combines information from two artificial intelligence models to fill in the missing details of photos in seconds while maintaining high accuracy and quality.

The scientists say traditional image restoration methods require careful tuning of an existing AI model by measuring the differences between generated and real images. This often leads to substandard results, they added.

The new approach uses a pre-trained version of Nvidia’s StyleGAN-2 algorithm to inform the group’s own model at many stages of the imaging process. This ensures that the “identity” of the people in the photo is preserved, with particular emphasis on facial features such as eyes and mouth.

The GFP-GAN demo is free. The researchers also released the source code of the model, which allows any developer to implement the recovery technology in their projects.

However, the creators of GFP-GAN warned that the algorithm could distort some details of faces and render the result in lower resolution.

Recall that Adobe introduced a tool for restoring old photos in Photoshop in June.

In October 2021, Israeli startup D-ID developed a tool to “talk” people in portraits.

In April, Deep Nostalgia taught Live Photos how to dance and blow kisses.