Adobe's new upscaling tech uses AI to sharpen video
VideoGigaGAN can enhance sharpness 8 times with fewer artifacts than before.
Most new features and experiments Adobe has announced recently involve AI, like object addition and removal for Premiere Pro and text-based image generation in Photoshop. Now, the company has unveiled VideoGigaGAN, an experimental AI feature it says can upscale video by eight times without the usual artifacts like flickering or distortion, The Verge reported.
VideoGigaGAN beats other Video Super Resolution (VSR) methods because it avoids the usual artifacts and flickering introduced by GAN (General Adversarial Networks), according to Adobe. At the same time, it adds sharpness and detail — where most other systems fail to do do both of those things at once.
Of course, the system is making up detail that doesn't exist out of whole cloth, so this wouldn't be suitable for things like forensic video enhancement, à la CSI-style crime shows. But the detail it does add looks impressively real, like skin textures, fine hairs, swan feather details and more.
The model builds on a large-scale image upsampler called GigaGAN, according to to Adobe's researchers. Previous VSR models have had difficulty generating rich details in results, so Adobe married "temporal attention" (reducing artifacts that accumulate over time), feature propagation (adding detail where none exists), anti-aliasing and something called "HF shuttle" (shuttling high-frequency features) to create the final result.
If added to products like Premiere Pro or After Effects, it could allow video producers to make low-resolution shots look a lot better, though using AI too enhance people is a controversial practice. There's no word yet on whether Adobe plans to do this (currently, the clips are short and only play at 12fps) but plenty of companies including NVIDIA, Microsoft, Blackmagic Design and others are working on AI upscaling technology as well.
