# Fusing Foveal Fixations Using Linear Retinal Transformations and Bayesian Experimental Design

arXiv: https://arxiv.org/abs/2505.01249 · HTML: https://mlsanity.com/paper/2505.01249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 39 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 10 of 10)

- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [CodeNeRF: Disentangled Neural Radiance Fields for Object Categories](https://mlsanity.com/paper/2109.01750/) (2021)
- [Modern Bayesian Experimental Design](https://mlsanity.com/paper/2302.14545/) (2023)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representations](https://mlsanity.com/paper/2207.10985/) (2022)
- [Uncertainty Guided Policy for Active Robotic 3D Reconstruction using Neural Radiance Fields](https://mlsanity.com/paper/2209.08409/) (2022)
- [SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry](https://mlsanity.com/paper/2302.10237/) (2023)
- [Towards Robust Image Classification Using Sequential Attention Models](https://mlsanity.com/paper/1912.02184/) (2019)
- [Structured Generative Models for Scene Understanding](https://mlsanity.com/paper/2302.03531/) (2023)

## Abstract (arXiv)

Humans (and many vertebrates) face the problem of fusing together multiple fixations of a scene in order to obtain a representation of the whole, where each fixation uses a high-resolution fovea and decreasing resolution in the periphery. In this paper we explicitly represent the retinal transformation of a fixation as a linear downsampling of a high-resolution latent image of the scene, exploiting the known geometry. This linear transformation allows us to carry out exact inference for the latent variables in factor analysis (FA) and mixtures of FA models of the scene. Further, this allows us to formulate and solve the choice of "where to look next" as a Bayesian experimental design problem using the Expected Information Gain criterion. Experiments on the Frey faces and MNIST datasets demonstrate the effectiveness of our models.