Color Visual Illusions: A Statistics-based Computational Model

Abstract

Visual illusions may be explained by the likelihood of patches in real-world images, as argued by input-driven paradigms in Neuro-Science. However, neither the data nor the tools existed in the past to extensively support these explanations. The era of big data opens a new opportunity to study input-driven approaches. We introduce a tool that computes the likelihood of patches, given a large dataset to learn from. Given this tool, we present a model that supports the approach and explains lightness and color visual illusions in a unified manner. Furthermore, our model generates visual illusions in natural images, by applying the same tool, reversely.

References in corpus (7)

• Conditional Image Generation with PixelCNN Decoders
• Pixel Recurrent Neural Networks
• NICE: Non-linear Independent Components Estimation
• Variational Lossy Autoencoder
• A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception
• Optical Illusions Images Dataset
• Synthesizing Visual Illusions Using Generative Adversarial Networks