The a16z Show · Sunday, September 13, 2026
Justin Johnson explained how Atlas addresses the issue of jumbled or distorted output in long video generations by implementing spatial control and grounding reference images in 3D space. Users can precisely steer the camera with pixel-level control, allowing for directorial command over the generated video content.
“So here, we built Atlas specifically around spatial control and the notion of a spatial context. So when we give Atlas reference images, they aren't just images. They're actually grounded in 3D space.”
“So then we showed some examples where even up to a minute of video, um, we give it more reference images and sort of leave breadcrumbs of those images along the trail in 3D. And then you get that directorial control over the video that you're generating.”