# Towards Metamerism via Foveated Style Transfer

arXiv: https://arxiv.org/abs/1705.10041 · HTML: https://mlsanity.com/paper/1705.10041/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2017.

## Built on by (most cited first, 9 of 9)

- [FoveaTer: Foveated Transformer for Image Classification](https://mlsanity.com/paper/2105.14173/) (2021)
- [On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation](https://mlsanity.com/paper/2112.07173/) (2021)
- [Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks](https://mlsanity.com/paper/2202.00838/) (2022)
- [Generalized Rectifier Wavelet Covariance Models For Texture Synthesis](https://mlsanity.com/paper/2203.07902/) (2022)
- [Noise-based Enhancement for Foveated Rendering](https://mlsanity.com/paper/2204.04455/) (2022)
- [Learning GAN-based Foveated Reconstruction to Recover Perceptually Important Image Features](https://mlsanity.com/paper/2108.03499/) (2021)
- [Learned Single-Pass Multitasking Perceptual Graphics for Immersive Displays](https://mlsanity.com/paper/2408.07836/) (2024)
- [How to augment your ViTs? Consistency loss and StyleAug, a random style transfer augmentation](https://mlsanity.com/paper/2112.09260/) (2021)
- [MAME: Multidimensional Adaptive Metamer Exploration with Human Perceptual Feedback](https://mlsanity.com/paper/2503.13212/) (2025)

## Abstract (arXiv)

The problem of textitvisual metamerism is defined as finding a family of perceptually indistinguishable, yet physically different images. In this paper, we propose our NeuroFovea metamer model, a foveated generative model that is based on a mixture of peripheral representations and style transfer forward-pass algorithms. Our gradient-descent free model is parametrized by a foveated VGG19 encoder-decoder which allows us to encode images in high dimensional space and interpolate between the content and texture information with adaptive instance normalization anywhere in the visual field. Our contributions include: 1) A framework for computing metamers that resembles a noisy communication system via a foveated feed-forward encoder-decoder network -- We observe that metamerism arises as a byproduct of noisy perturbations that partially lie in the perceptual null space; 2) A perceptual optimization scheme as a solution to the hyperparametric nature of our metamer model that requires tuning of the image-texture tradeoff coefficients everywhere in the visual field which are a consequence of internal noise; 3) An ABX psychophysical evaluation of our metamers where we also find that the rate of growth of the receptive fields in our model match V1 for reference metamers and V2 between synthesized samples. Our model also renders metamers at roughly a second, presenting a ×1000 speed-up compared to the previous work, which allows for tractable data-driven metamer experiments.