AI & Enterprise
Netflix releases VOID video AI model as open source
Netflix has unveiled VOID, an AI model designed to delete specific objects from video and reconstruct the remaining scene in a physically natural way, The Register reported on April 3. VOID is a vision-language model that also generates how other elements would have moved if the removed object had not been there. Netflix and Sofia University researchers described it as a video object removal framework for complex situations. Netflix released it on Hugging Face, and researchers said a survey of 25 people showed 64.8 percent preferred VOID.
