You can find AI that creates new images, but what if you want to fix an old family photo? You may have a no-fee option. Louis Bouchard and PetaPixel drew attention to a free tool recently developed by Tencent researchers, GFP-GAN (Generative Facial Prior-Generative Adversarial Network), which can restore damaged and low-resolution portraits. The technology merges information from two AI models to fill in the missing details of the photo with realistic details in seconds, while maintaining high accuracy and quality.
Conventional methods refine an existing AI image restoration model by measuring the differences between artificial and real photos. This often leads to low-quality results, the researchers said. The new approach uses a pre-trained version of an existing model (NVIDIA’s StyleGAN-2) to inform the team’s proprietary model at multiple stages during the image generation process. The technique aims to preserve the “identity” of the people in the photo, paying special attention to facial features such as the eyes and mouth.
This project is still bound by the limitations of current AI. While surprisingly accurate, it makes educated guesses about missing content. The researchers warn that you may see “slight identity change” and a lower resolution than you’d like. Don’t rely on this to print a poster-sized photo of your grandparents, folks. Still, the work here is promising—it hints at a future where you can easily rescue images that would otherwise be lost to the ravages of time.
All products recommended by Engadget are selected by our editorial team, independent of our parent company. Some of our stories contain affiliate links. If you buy something through one of these links, we may earn an affiliate commission.