Abstract
When judging material properties of a translucent object, we often look at sharp geometric features such as edges. Image analysis shows edges of translucent objects exhibit distinctive light scattering profiles. Around the edges, there is often rapid change of material thickness, which provides valuable information for recovering material properties. Previous study found that perception of 3D mesoscopic shape is different between opaque and translucent objects. Here, we examine whether geometry affects perception of translucent material perception. The images used in the experiment are computer-generated using Mitsuba physically based renderer. The shape of an object is described as 2D height fields (in which each pixel contains the amount of extrusion from the object surface to the base plane). We varied both material properties and 3D shapes of the stimuli: for the former, we used materials with varying optical densities (used by the radiative transfer model) so that the object would have different levels of ground-truth translucency; for the latter, we applied different amounts of Gaussian blur to the underlying height fields. Seven observers finished a paired-comparison experiment where they viewed a pair of images that had different ground-truth translucency and blur levels. They were asked to judge which object appeared to be more translucent. We also included control conditions where the objects in both images have the same blur levels. We found that when there was no difference in the level of blurring between the images, observers could discriminate material properties of the two objects well (mean accuracy =81%). However, when the two objects differ in the blur level, all observers started to make more mistakes (mean accuracy = 71%). We conclude that observers' sensitivity to translucent appearance is affected by the sharpness of the 3D geometry of the object, thus suggesting 3D shape affects material perception for translucency.
Meeting abstract presented at VSS 2018