Skip to main content
. 2018 Dec 17;116(1):96–105. doi: 10.1073/pnas.1802103115

Fig. 2.

Fig. 2.

(A) A motorcycle image viewed through the lens of a face model. While it sees face viewlets everywhere, it does not detect any faces because the viewlets do not match structurally. (B) The same image viewed through a motorcycle model.