Metaphysic Blog The Challenges of Getting Neural Humans to Hug

It can be difficult to control the camera viewpoint in text-to-video systems, which chiefly rely on the user's text instructions to generate tracking shots. A more precise way of imposing camera viewpoint is to extract motion from an existing video into the generated video. However, the newest crop of T2V systems cannot use prior methods that obtain this functionality, because their architectures are different. Therefore, researchers have now presented a novel and - they argue - superior method of directing the camera view of generated videos.The post The Challenges of Getting Neural Humans to Hug first appeared on Metaphysic.ai.