Computer Science > Computer Vision and Pattern Recognition
Title:Multiview Retrieval of Referent Geometry from Articulated Silhouettes
Abstract:A silhouette typically constrains the geometry of the object that intercepts the light. When an articulated surrogate is used to depict an object, the cast shadow is evidence about two geometries: the occluder and its intended referent. We formulate referent retrieval for a calibrated screen and a catalog of three-dimensional animal models. Forty participants produced 2,880 hand-shadow poses while viewing prescribed orthographic projections of the models. A dual encoder aligns pose silhouettes and model geometry without requiring point correspondences between the two. Under a joint performer and model holdout, three instructed poses and three light positions yield exact retrieval in 111 of 144 sets, compared with 70 of 144 for a contour matcher (28.5 percentage points difference, 95% crossed-bootstrap interval 17.4 to 40.3). Oblique illumination decreases direct contour overlap but improves retrieval even when the instructed view is held fixed. An asymmetry in the separation of the fingers that represent ears helps distinguish two rabbit models whose central shadows are frequently interchangeable. The distinction has no counterpart in a reconstruction of the occluding volume.
Submission history
From: Inês Valcorvo[v1] Thu, 29 Oct 2026 01:58:31 UTC (151 KB)