Abstract
Shape cues play an important role in computer vision, but shape is not the only information available in images.Materials, such as fabric and plastic, are discernible inimages even when shapes, such as those of an object, are not. We argue that it would be ideal to recognize materialswithout relying on object cues such as shape. This wouldallow us to use materials as a context for other vision tasks,such as object recognition. Humans are intuitively able tofind visual cues that describe materials. Previous frame-works attempt to recognize these cues (as visual materialtraits) using fully-supervised learning. This requirement isnot feasible when multiple annotators and large quantitiesof images are involved. In this paper, we derive a framework that allows us to discover locally-recognizable material attributes from crowdsourced perceptual material distances. We show that the attributes we discover do in fact separate material categories. Our learned attributes exhibit the same desirable properties as material traits, despite the fact that they are discovered using only partial supervision.