Upsampling method sharpens AI vision with up to 16 times less GPU memory

From facial recognition on smartphones to humanoid robots, computer vision technology, which serves as the eyes of artificial intelligence (AI), is widely used in daily life. A joint research team from KAIST and international institutions has developed a technology that allows AI to see the world more clearly with minimal memory, increasing GPU (Graphics Processing Unit) memory efficiency by up to 16 times. The achievement is seen as a core technology that could accelerate the era of humanoid robots and on-device AI.