We trust AI to act like human brains, but it turns out they're completely blind to the textures we see every day.
April 3, 2026
Original Paper
Perceptual misalignment of texture representations in convolutional neural networks
arXiv · 2604.01341
The Takeaway
Even when AI matches human brain activity patterns, it fails to perceive textures the same way we do. This reveals that our dominant theories of vision are missing the fundamental mechanisms that allow humans to understand the visual world.
From the abstract
Mathematical modeling of visual textures traces back to Julesz's intuition that texture perception in humans is based on local correlations between image features. An influential approach for texture analysis and generation generalizes this notion to linear correlations between the nonlinear features computed by convolutional neural networks (CNNs), compiled into Gram matrices. Given that CNNs are often used as models for the visual system, it is natural to ask whether such "texture representati