arXiv subjects

Roberto Pierdicca

Publications and source records attributed to Roberto Pierdicca.

3 recordsLinked to original sources

arXiv2026

EEG2Vision: A Multimodal EEG-Based Framework for 2D Visual Reconstruction in Cognitive Neuroscience

Reconstructing visual stimuli from non-invasive electroencephalography (EEG) remains challenging due to its low spatial resolution and high noise, particularly under realistic low-density electrode configurations. To address this, we present EEG2Vision, a modular, end-to-end EEG-to-image framework that systematically evaluates reconstruction performance across different EEG resolutions (128, 64, 32, and 24 channels) and enhances visual quality through a prompt-guided post-reconstruction boosting mechanism. Starting from EEG-conditioned diffusion reconstruction, the boosting stage uses a multimodal large language model to extract semantic descriptions and leverages image-to-image diffusion to refine geometry and perceptual coherence while preserving EEG-grounded structure. Our experiments show that semantic decoding accuracy degrades significantly with channel reduction (e.g., 50-way Top-1 Acc from 89% to 38%), while reconstruction quality slight decreases (e.g., FID from 76.77 to 80.51). The proposed boosting consistently improves perceptual metrics across all configurations, achieving up to 9.71% IS gains in low-channel settings. A user study confirms the clear perceptual preference for boosted reconstructions. The proposed approach significantly boosts the feasibility of real-time brain-2-image applications using low-resolution EEG devices, potentially unlocking this type of applications outside laboratory settings.

cs.CV↗

arXiv2026

Brain3D: EEG-to-3D Decoding of Visual Representations via Multimodal Reasoning

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.

cs.CV↗

arXiv2023

A New Technique of the Virtual Reality Visualization of Complex Volume Images from the Computer Tomography and Magnetic Resonance Imaging

This paper presents a new technique for the virtual reality (VR) visu-alization of complex volume images obtained from computer tomography (CT) and Magnetic Resonance Imaging (MRI) by combining three-dimensional (3D) mesh processing and software coding within the gaming engine. The method operates on real representations of human organs avoiding any structural ap-proximations of the real physiological shape. In order to obtain realistic repre-sentation of the mesh model, geometrical and topological corrections are per-formed on the mesh surface with preserving real shape and geometric structure. Using mathematical intervention on the 3D model and mesh triangulation the second part of our algorithm ensures an automatic construction of new two-dimensional (2D) shapes that represent vector slices along any user chosen di-rection. The final result of our algorithm is developed software application that allows to user complete visual experience and perceptual exploration of real human organs through spatial manipulation of their 3D models. Thus our pro-posed method achieves a threefold effect: i) high definition VR representation of real models of human organs, ii) the real time generated slices of such a model along any directions, and iii) almost unlimited amount of training data for machine learning that is very useful in process of diagnosis. In addition, our developed application also offers significant benefits to educational process by ensuring interactive features and quality perceptual user experience.

cs.MM↗