Preprint
Oct 2026
Rendering-Free Lookahead for Question-Guided Active Vision
Active robot vision requires controlling the camera to reveal task-relevant information that is hidden from the current viewpoint. For example, determining what is inside a box may require raising the camera and looking down into it. For viewpoint-dependent question answering, the challenge is to select camera motions...
Koya Sakamoto, Daich Azuma, Shuhei Kurita et al.
· 0 citations