Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding

2026-04-20

AI Summary

Existing visual decoding approaches often overlook the intrinsic computational mechanisms of the human visual system, struggling to bridge the systematic and stochastic gaps between neural signals and visual modalities. This work proposes a brain-inspired capture (BI-Cap) paradigm that explicitly integrates human visual processing principles into the decoding pipeline for the first time. The framework establishes a neuromorphic pipeline incorporating four biologically plausible dynamic and static transformations, complemented by mutual information–guided dynamic blur modulation and evidence-driven latent space representations. Evaluated on two public benchmarks, the method achieves zero-shot brain-to-image retrieval, outperforming state-of-the-art approaches by 9.2% and 8.0%, respectively, thereby substantially enhancing the robustness and generalization of cross-modal decoding.

Technology Category

• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Visual decoding of neurophysiological signals is a critical challenge for brain-computer interfaces (BCIs) and computational neuroscience. However, current approaches are often constrained by the systematic and stochastic gaps between neural and visual modalities, largely neglecting the intrinsic computational mechanisms of the Human Visual System (HVS). To address this, we propose Brain-Inspired Capture (BI-Cap), a neuromimetic perceptual simulation paradigm that aligns these modalities by emulating HVS processing. Specifically, we construct a neuromimetic pipeline comprising four biologically plausible dynamic and static transformations, coupled with Mutual Information (MI)-guided dynamic blur regulation to simulate adaptive visual processing. Furthermore, to mitigate the inherent non-stationarity of neural activity, we introduce an evidence-driven latent space representation. This formulation explicitly models uncertainty, thereby ensuring robust neural embeddings. Extensive evaluations on zero-shot brain-to-image retrieval across two public benchmarks demonstrate that BI-Cap substantially outperforms state-of-the-art methods, achieving relative gains of 9.2\% and 8.0\%, respectively. We have released the source code on GitHub through the link https://github.com/flysnow1024/BI-Cap.

Problem

• visual decoding
• brain-computer interfaces
• neural-visual gap
• Human Visual System
• neurophysiological signals

Innovation

• neuromimetic
• visual decoding
• human visual system
• mutual information
• evidence-driven representation