Brain3D: EEG-to-3D Decoding of Visual Representations via Multimodal Reasoning
2026-04-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed Brain3D, a system that turns brain signals (EEG) into 3D objects. Instead of going straight from EEG to 3D, their method first creates images from the brain data, then uses a language model to understand 3D shapes, and finally builds 3D models from those shapes. This step-by-step approach helps them make accurate 3D reconstructions that match what the person actually saw. Their tests show the system works well at interpreting brain signals for creating 3D objects.
EEG3D reconstructionmultimodal learninggenerative modelslarge language modelsdiffusion modelsimage-to-3D conversionCLIPScoresemantic alignmenttop-1 accuracy
Authors
Emanuele Balloni, Emanuele Frontoni, Chiara Matti, Marina Paolanti, Roberto Pierdicca, Emiliano Santarnecchi
Abstract
Decoding visual information from electroencephalography (EEG) has recently achieved promising results, primarily focusing on reconstructing two-dimensional (2D) images from brain activity. However, the reconstruction of three-dimensional (3D) representations remains largely unexplored. This limits the geometric understanding and reduces the applicability of neural decoding in different contexts. To address this gap, we propose Brain3D, a multimodal architecture for EEG-to-3D reconstruction based on EEG-to-image decoding. It progressively transforms neural representations into the 3D domain using geometry-aware generative reasoning. Our pipeline first produces visually grounded images from EEG signals, then employs a multimodal large language model to extract structured 3D-aware descriptions, which guide a diffusion-based generation stage whose outputs are finally converted into coherent 3D meshes via a single-image-to-3D model. By decomposing the problem into structured stages, the proposed approach avoids direct EEG-to-3D mappings and enables scalable brain-driven 3D generation. We conduct a comprehensive evaluation comparing the reconstructed 3D outputs against the original visual stimuli, assessing both semantic alignment and geometric fidelity. Experimental results demonstrate strong performance of the proposed architecture, achieving up to 85.4% 10-way Top-1 EEG decoding accuracy and 0.648 CLIPScore, supporting the feasibility of multimodal EEG-driven 3D reconstruction.