Dual-Stream EEG Decoding for 3D Visual Perception
This work provides a bio-inspired framework for decoding 3D visual perception from EEG, offering interpretable insights into neural processing for brain-computer interfaces.
The paper introduces a dual-stream EEG decoding model that separately decodes object identity and spatial orientation from EEG signals during 3D shape perception, enabling 3D reconstruction via EEG-conditioned diffusion. The approach achieves successful decoding of both attributes and reveals dynamic neural involvement patterns.
This paper explores a novel brain decoding model for 3D shape perception through a dual pathway architecture mirroring biological vision. Our bio-inspired approach implements separate decoding modules for object identity and spatial orientation, inspired by ventral and dorsal pathways, during continuous rotations. We employ circular regression for angle prediction and develop EEG-conditioned multiview diffusion for 3D reconstruction. Our approach successfully decodes both object identity and spatial orientation from EEG signals and enables 3D reconstruction from neural activity, with interpretability analyses revealing temporally structured involvement of ventral, dorsal, and motor-related channels rather than a static ventral dominance in supporting object and angle decoding.