SpatialScout tests VLM agents on active 3D scene mapping
Claude Opus 5.5 scores 41.71% mean overlap; only 3.25% of targets exceed IoU 0.9.
Stories per day · 30 days
Related3d-mapping1benchmark1beyondsce1computer-vision1grasping1robotics1spatial-reasoning1vlm-agents1zero-shot1
2 stories, newest first · one card per story
Stories tagged #active-perception
Beyond the Current Scene: Event-Referential Grasping with Active View Selection
BeyondSCe enables zero-shot robotic grasping of event-referenced objects, including occluded targets, using pretrained models and active view selection.