"VOID stands for Video Object and Interaction Deletion. It's a VLM (vision-language model) that can not only erase objects from a scene but can also inpaint how remaining objects in the scene should behave without the influence of whatever was excised."
"The video model's creators describe VOID in a preprint paper as 'a video object removal framework designed to perform physically-plausible inpainting of video content.' This allows filmmakers to alter scenes dynamically."
Netflix's VOID model, which stands for Video Object and Interaction Deletion, enables filmmakers to modify scenes by erasing objects and generating new content. This technology allows for seamless transitions, such as changing a dramatic car crash into a peaceful driving scene without the need for reshoots or extensive CGI. The model can create physically plausible scenarios by inpainting the behavior of remaining objects, thus transforming the narrative direction of films efficiently and creatively.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]