Dual-Stream EEG Decoding for 3D Visual Perception

• URL: http://arxiv.org/abs/2606.22182v1
• Date: Sat, 20 Jun 2026 18:25:16 GMT
• Title: Dual-Stream EEG Decoding for 3D Visual Perception
• Abstract summary: Bio-inspired approach implements separate decoding modules for object identity and spatial orientation.<n>We employ circular regression for angle prediction and develop EEG-conditioned multiview diffusion for 3D reconstruction.
• Score: 1.6463973642489373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Seeing Before Generating: Object Perception Enhances Single-View 3D Reconstruction [6.264701896062822]
  We show that learnt object perception can significantly enhance 3D reconstruction.<n>We propose a method that leverages perceptual signals extracted from pretrained perception models.<n>Our approach is model-agnostic and can be integrated into various reconstruction methods in a plug-and-play manner.
  arXiv  Detail & Related papers  (2026-07-21T01:55:24Z)
• SeeSE3: Emergence of 3D Space in Vision Features [54.140615953727355]
  We investigate the relation between the structure of the space of visual features and the group of Euclidean transformations $SE(3)$.<n>We show that self-supervised vision models, which, in principle, have not been trained with direct 3D supervision or active agency, possess latent subspaces that are remarkably strongly correlated with 3D Euclidean space, when probed correctly.<n>We propose a new class of "Latent-Space Navigation" techniques that perform visual odometry and localization purely in the latent space, bypassing the need for explicit 3D reconstruction.
  arXiv  Detail & Related papers  (2026-07-15T18:00:31Z)
• Pano3D: Unified 3D Reconstruction and Panoptic Segmentation [68.18993232814061]
  We introduce an approach that performs 3D reconstruction and 3D panoptic segmentation in a unified framework.<n>We build on existing 3D reconstruction models and augment them with a set-based mask decoder.<n>Our method achieves state-of-the-art performance in 3D panoptic segmentation across ScanNet, ScanNet200, and ScanNet++ datasets.
  arXiv  Detail & Related papers  (2026-06-12T09:43:13Z)
• Brain3D: EEG-to-3D Decoding of Visual Representations via Multimodal Reasoning [14.30030169416955]
  We propose Brain3D, a multimodal architecture for EEG-to-3D reconstruction based on EEG-to-image decoding.<n>Our pipeline first produces visually grounded images from EEG signals, then employs a multimodal large language model to extract structured 3D-aware descriptions.<n>By decomposing the problem into structured stages, the proposed approach avoids direct EEG-to-3D mappings and enables scalable brain-driven 3D generation.
  arXiv  Detail & Related papers  (2026-04-09T10:35:44Z)
• MedTet: An Online Motion Model for 4D Heart Reconstruction [59.74234226055964]
  We present a novel approach to reconstruction of 3D cardiac motion from sparse intraoperative data.<n>Existing methods can accurately reconstruct 3D organ geometries from full 3D volumetric imaging.<n>We propose a versatile framework for reconstructing 3D motion from such partial data.
  arXiv  Detail & Related papers  (2024-12-03T17:18:33Z)
• Neuro-3D: Towards 3D Visual Decoding from EEG Signals [49.502364730056044]
  We introduce a new neuroscience task: decoding 3D visual perception from EEG signals.<n>We first present EEG-3D, a dataset featuring multimodal analysis data and EEG recordings from 12 subjects viewing 72 categories of 3D objects rendered in both videos and images.<n>We propose Neuro-3D, a 3D visual decoding framework based on EEG signals.
  arXiv  Detail & Related papers  (2024-11-19T05:52:17Z)
• EEG-Driven 3D Object Reconstruction with Style Consistency and Diffusion Prior [1.7205106391379026]
  This paper proposes an EEG-based 3D object reconstruction method with style consistency and diffusion priors. Through experimental validation, we demonstrate that this method can effectively use EEG data to reconstruct 3D objects with style consistency.
  arXiv  Detail & Related papers  (2024-10-28T12:59:24Z)
• Geometry-Biased Transformer for Robust Multi-View 3D Human Pose Reconstruction [3.069335774032178]
  We propose a novel encoder-decoder Transformer architecture to estimate 3D poses from multi-view 2D pose sequences. We conduct experiments on three benchmark public datasets, Human3.6M, CMU Panoptic and Occlusion-Persons.
  arXiv  Detail & Related papers  (2023-12-28T16:30:05Z)
• MinD-3D: Reconstruct High-quality 3D objects in Human Brain [50.534007259536715]
  Recon3DMind is an innovative task aimed at reconstructing 3D visuals from Functional Magnetic Resonance Imaging (fMRI) signals. We present the fMRI-Shape dataset, which includes data from 14 participants and features 360-degree videos of 3D objects. We propose MinD-3D, a novel and effective three-stage framework specifically designed to decode the brain's 3D visual information from fMRI signals.
  arXiv  Detail & Related papers  (2023-12-12T18:21:36Z)
• Learning Internal Representations of 3D Transformations from 2D Projected Inputs [13.029330360766595]
  We show how our model infers depth from moving 2D projected points, learns 3D rotational transformations from 2D training stimuli, and compares to human performance on psychophysical structure-from-motion experiments.
  arXiv  Detail & Related papers  (2023-03-31T02:43:01Z)
• DeepRecon: Joint 2D Cardiac Segmentation and 3D Volume Reconstruction via A Structure-Specific Generative Method [12.26150675728958]
  We propose an end-to-end latent-space-based framework, DeepRecon, that generates multiple clinically essential outcomes. Our method identifies the optimal latent representation of the cine image that contains accurate semantic information for cardiac structures. In particular, our model jointly generates synthetic images with accurate semantic information and segmentation of the cardiac structures.
  arXiv  Detail & Related papers  (2022-06-14T20:46:11Z)
• 3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks [52.710012864395246]
  We propose a fully automated pipeline for both detection and matching of curvilinear structures in stereo pairs. We mainly focus on 3D reconstruction of dislocations from stereo pairs of TEM images.
  arXiv  Detail & Related papers  (2021-10-14T23:05:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.