# Contrast Sensitivity Functions in Autoencoders

arXiv: https://arxiv.org/abs/2103.00481 · HTML: https://mlsanity.com/paper/2103.00481/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2021.

## Built on by (most cited first, 13 of 13)

- [On the relation between statistical learning and perceptual distances](https://mlsanity.com/paper/2106.04427/) (2021)
- [Do computer vision foundation models learn the low-level characteristics of the human visual system?](https://mlsanity.com/paper/2502.20256/) (2025)
- [The Art of Deception: Color Visual Illusions and Diffusion Models](https://mlsanity.com/paper/2412.10122/) (2024)
- [ColorSense: A Study on Color Vision in Machine Visual Recognition](https://mlsanity.com/paper/2212.08650/) (2022)
- [Orthonormal Convolutions for the Rotation Based Iterative Gaussianization](https://mlsanity.com/paper/2206.03860/) (2022)
- [Do Vision Transformers See Like Humans? Evaluating their Perceptual Alignment](https://mlsanity.com/paper/2508.09850/) (2025)
- [Image Statistics Predict the Sensitivity of Perceptual Quality Metrics](https://mlsanity.com/paper/2303.09874/) (2023)
- [Contrast Sensitivity in Multimodal Large Language Models: A Psychophysics-Inspired Evaluation](https://mlsanity.com/paper/2508.10367/) (2025)
- [Low-Pass Filtering Improves Behavioral Alignment of Vision Models](https://mlsanity.com/paper/2602.13859/) (2026)
- [Paraphrasing Magritte's Observation](https://mlsanity.com/paper/2202.08103/) (2022)
- [Analysis of Deep Image Quality Models](https://mlsanity.com/paper/2302.13345/) (2023)
- [Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment](https://mlsanity.com/paper/2412.03210/) (2024)
- [From Images to Perception: Emergence of Perceptual Properties by Reconstructing Images](https://mlsanity.com/paper/2508.10450/) (2025)

## Abstract (arXiv)

Three decades ago, Atick et al. suggested that human frequency sensitivity may emerge from the enhancement required for a more efficient analysis of retinal images. Here we reassess the relevance of low-level vision tasks in the explanation of the Contrast Sensitivity Functions (CSFs) in light of (1) the current trend of using artificial neural networks for studying vision, and (2) the current knowledge of retinal image representations. As a first contribution, we show that a very popular type of convolutional neural networks (CNNs), called autoencoders, may develop human-like CSFs in the spatio-temporal and chromatic dimensions when trained to perform some basic low-level vision tasks (like retinal noise and optical blur removal), but not others (like chromatic adaptation or pure reconstruction after simple bottlenecks). As an illustrative example, the best CNN (in the considered set of simple architectures for enhancement of the retinal signal) reproduces the CSFs with an RMSE error of 11% of the maximum sensitivity. As a second contribution, we provide experimental evidence of the fact that, for some functional goals (at low abstraction level), deeper CNNs that are better in reaching the quantitative goal are actually worse in replicating human-like phenomena (such as the CSFs). This low-level result (for the explored networks) is not necessarily in contradiction with other works that report advantages of deeper nets in modeling higher-level vision goals. However, in line with a growing body of literature, our results suggests another word of caution about CNNs in vision science since the use of simplified units or unrealistic architectures in goal optimization may be a limitation for the modeling and understanding of human vision.