Perceptual Reality Transformer: Neural Architectures for Simulating Neurological Perception Conditions
This work addresses the need for better understanding and empathy in medical contexts by providing a systematic benchmark for simulating neurological perception conditions, with applications in education and assistive technology.
The paper tackled the problem of simulating neurological perception conditions by developing the Perceptual Reality Transformer, a framework using neural architectures to map natural images to condition-specific perceptual states, achieving optimal performance with Vision Transformers on ImageNet and CIFAR-10 datasets.
Neurological conditions affecting visual perception create profound experiential divides between affected individuals and their caregivers, families, and medical professionals. We present the Perceptual Reality Transformer, a comprehensive framework employing six distinct neural architectures to simulate eight neurological perception conditions with scientifically-grounded visual transformations. Our system learns mappings from natural images to condition-specific perceptual states, enabling others to experience approximations of simultanagnosia, prosopagnosia, ADHD attention deficits, visual agnosia, depression-related changes, anxiety tunnel vision, and Alzheimer's memory effects. Through systematic evaluation across ImageNet and CIFAR-10 datasets, we demonstrate that Vision Transformer architectures achieve optimal performance, outperforming traditional CNN and generative approaches. Our work establishes the first systematic benchmark for neurological perception simulation, contributes novel condition-specific perturbation functions grounded in clinical literature, and provides quantitative metrics for evaluating simulation fidelity. The framework has immediate applications in medical education, empathy training, and assistive technology development, while advancing our fundamental understanding of how neural networks can model atypical human perception.