mlsanityData to 7 Oct 2026

EEG-Driven Image Reconstruction with Saliency-Guided Diffusion Models

arXiv 2510.26391 ↗First posted 30 Oct 2025cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Existing EEG-driven image reconstruction methods often overlook spatial attention mechanisms, limiting fidelity and semantic coherence. To address this, we propose a dual-conditioning framework that combines EEG embeddings with spatial saliency maps to enhance image generation. Our approach leverages the Adaptive Thinking Mapper (ATM) for EEG feature extraction and fine-tunes Stable Diffusion 2.1 via Low-Rank Adaptation (LoRA) to align neural signals with visual semantics, while a ControlNet branch conditions generation on saliency maps for spatial control. Evaluated on THINGS-EEG, our method achieves a significant improvement in the quality of low- and high-level image features over existing approaches. Simultaneously, strongly aligning with human visual attention. The results demonstrate that attentional priors resolve EEG ambiguities, enabling high-fidelity reconstructions with applications in medical diagnostics and neuroadaptive interfaces, advancing neural decoding through efficient adaptation of pre-trained diffusion models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 14 of its 32 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

14 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Natural scene reconstruction from fMRI signals using generative latent diffusion9 Mar

Other references · 13

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2017SalGAN: Visual Saliency Prediction with Generative Adversarial Networkscited by 63
  10. 2015CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Researchcited by 52
  11. 2018EML-NET:An Expandable Multi-Layer NETwork for Saliency Predictioncited by 51
  12. 2024GazeFusion: Saliency-Guided Image Generationcited by 4
1 more
  1. 2024CrossPT-EEG: A Benchmark for Cross-Participant and Cross-Time Generalization of EEG-based Visual Decodingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion
  2. 2026EEG2Vision: A Multimodal EEG-Based Framework for 2D Visual Reconstruction in Cognitive Neuroscience
  3. 2025Interpretable EEG-to-Image Generation with Semantic Prompts
  4. 2025SYNAPSE: Synergizing an Adapter and Finetuning for High-Fidelity EEG Synthesis from a CLIP-Aligned Encoder
  5. 2026Brain-to-Image Generation: Reconstructing Visual Stimuli from EEG using Generative Adversarial Networks
  6. 2024EEG-Driven 3D Object Reconstruction with Style Consistency and Diffusion Prior
  7. 2023Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals
  8. 2026MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion