NeuralDiffuser: Controllable fMRI Reconstruction with Primary Visual Feature Guided Diffusion

Autor:	Li, Haoyu, Wu, Hao, Chen, Badong
Rok vydání:	2024
Předmět:	Computer Science - Neural and Evolutionary Computing Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Reconstructing visual stimuli from functional Magnetic Resonance Imaging (fMRI) based on Latent Diffusion Models (LDM) provides a fine-grained retrieval of the brain. A challenge persists in reconstructing a cohesive alignment of details (such as structure, background, texture, color, etc.). Moreover, LDMs would generate different image results even under the same conditions. For these, we first uncover the neuroscientific perspective of LDM-based methods that is top-down creation based on pre-trained knowledge from massive images but lack of detail-driven bottom-up perception resulting in unfaithful details. We propose NeuralDiffuser which introduces primary visual feature guidance to provide detail cues in the form of gradients, extending the bottom-up process for LDM-based methods to achieve faithful semantics and details. We also developed a novel guidance strategy to ensure the consistency of repeated reconstructions rather than a variety of results. We obtain the state-of-the-art performance of NeuralDiffuser on the Natural Senses Dataset (NSD), which offers more faithful details and consistent results. Comment: The implementation error lead to incorrect results in experiment
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.13809 Zobrazit plný text záznamu View this record from Arxiv