From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images

TL;DR

This paper introduces PerceptNet, a bio-inspired neural architecture trained on image reconstruction tasks, which naturally develops perceptual properties aligning with human judgments without explicit perceptual training.

Contribution

The work presents a novel biologically inspired model that captures perceptual judgments through image reconstruction tasks, revealing emergent perceptual properties similar to human perception.

Findings

Encoder layer correlates with human perceptual judgments.

Optimal perception alignment occurs at moderate noise, blur, and sparsity levels.

Biologically inspired models can learn perceptual metrics without supervision.

Abstract

A number of scientists suggested that human visual perception may emerge from image statistics, shaping efficient neural representations in early vision. In this work, a bio-inspired architecture that can accommodate several known facts in the retina-V1 cortex, the PerceptNet, has been end-to-end optimized for different tasks related to image reconstruction: autoencoding, denoising, deblurring, and sparsity regularization. Our results show that the encoder stage (V1-like layer) consistently exhibits the highest correlation with human perceptual judgments on image distortion despite not using perceptual information in the initialization or training. This alignment exhibits an optimum for moderate noise, blur and sparsity. These findings suggest that the visual system may be tuned to remove those particular levels of distortion with that level of sparsity and that biologically inspired models can learn perceptual metrics without human supervision.