Apparent distortion of the frontoparallel plane from wide-field motion parallax

Abstract

We studied the visual perception of large frontoparallel planes from monocular motion parallax, during self-motion and object motion. The isodistortion framework predicts that a frontoparallel plane should be perceived as convex in the motion direction for near viewing distances, with decreasing convexity as the viewing distance increases. The stimuli represented dotted planes or dihedrals with a vertical or horizontal curvature. In condition SM (self-motion) the subject translated his/her head laterally. This movement was recorded and used to generate images simulating the presence of stationary surfaces. In condition OM (object-motion), the subject was stationary, and his recorded motion was applied to rotate the surfaces in depth, reproducing the SM optic flow obtained if gaze stabilization was perfect. Image size was 70 deg, and viewing distances were 0.5m or 4 m. Subjects indicated whether the surfaces were concave or convex in the horizontal or vertical direction, the surfaces being planes and horizontally (respectively vertically) curved dihedrals. A few depth reversals occurred at large dihedral angles in condition OM. The frontoparallel plane was perceived as convex in conditions SM and OM in both directions (horizontal and vertical). The thresholds of the response curves were significantly negative, indicating that the AFP (apparent frontoparallel plane) was always a concave surface. The results were similar for conditions SM and OM. The slope of the psychometric curves tended to be higher for the vertically curved dihedrals, as compared to the horizontally curved. Motion parallax yields an apparent distortion of large frontoparallel planes. This distortion is similar during self-motion and object-motion, and may not be due to the integration of non-visual signals related to self-motion. The similarity of the distortion in the vertical and horizontal directions questions the iso-distortion model, as well as the spin variation model.