Unsupervised learning reveals interpretable latent representations for translucency perception
Sign Up to like & getrecommendations! Published in 2022 at "PLOS Computational Biology"
DOI: 10.1371/journal.pcbi.1010878
Abstract: Humans constantly assess the appearance of materials to plan actions, such as stepping on icy roads without slipping. Visual inference of materials is challenging because a given material can appear dramatically different in various scenes.… read more here.
Keywords: learning reveals; material; reveals interpretable; translucency ... See more keywords