Animate Your Thoughts: Decoupled Reconstruction of Dynamic Natural Vision from Slow Brain Activity

• URL: http://arxiv.org/abs/2405.03280v2
• Date: Wed, 19 Feb 2025 05:02:08 GMT
• Title: Animate Your Thoughts: Decoupled Reconstruction of Dynamic Natural Vision from Slow Brain Activity
• Authors: Yizhuo Lu, Changde Du, Chong Wang, Xuanliu Zhu, Liuyun Jiang, Xujin Li, Huiguang He,
• Abstract summary: We propose a two-stage model named Mind-Animator to reconstruct human dynamic vision from brain activity. During the fMRI-to-feature stage, we decouple semantic, structure, and motion features from fMRI. In the feature-to-video stage, these features are integrated into videos using an inflated Stable Diffusion.
• Score: 13.04953215936574
• License:
• Abstract: Reconstructing human dynamic vision from brain activity is a challenging task with great scientific significance. Although prior video reconstruction methods have made substantial progress, they still suffer from several limitations, including: (1) difficulty in simultaneously reconciling semantic (e.g. categorical descriptions), structure (e.g. size and color), and consistent motion information (e.g. order of frames); (2) low temporal resolution of fMRI, which poses a challenge in decoding multiple frames of video dynamics from a single fMRI frame; (3) reliance on video generation models, which introduces ambiguity regarding whether the dynamics observed in the reconstructed videos are genuinely derived from fMRI data or are hallucinations from generative model. To overcome these limitations, we propose a two-stage model named Mind-Animator. During the fMRI-to-feature stage, we decouple semantic, structure, and motion features from fMRI. Specifically, we employ fMRI-vision-language tri-modal contrastive learning to decode semantic feature from fMRI and design a sparse causal attention mechanism for decoding multi-frame video motion features through a next-frame-prediction task. In the feature-to-video stage, these features are integrated into videos using an inflated Stable Diffusion, effectively eliminating external video data interference. Extensive experiments on multiple video-fMRI datasets demonstrate that our model achieves state-of-the-art performance. Comprehensive visualization analyses further elucidate the interpretability of our model from a neurobiological perspective. Project page: https://mind-animator-design.github.io/.

Related papers

• NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction [29.030311713701295]
  We propose NeuroClips, an innovative framework to decode high-fidelity and smooth video from fMRI. NeuroClips utilizes a semanticsor to reconstruct videos, guiding semantic accuracy and consistency, and employs a perception reconstructor to capture low-level perceptual details. NeuroClips achieves smooth high-fidelity video reconstruction of up to 6s at 8FPS, gaining significant improvements over state-of-the-art models in various metrics.
  arXiv  Detail & Related papers  (2024-10-25T10:28:26Z)
• Reanimating Images using Neural Representations of Dynamic Stimuli [36.04425924379253]
  Video diffusion models are used to decouple static image representation from motion generation. Brain-decoded motion signals enable realistic video reanimation based only on the initial frame of the video. This framework advances our understanding of how the brain represents spatial and temporal information in dynamic visual scenes.
  arXiv  Detail & Related papers  (2024-06-04T17:59:49Z)
• MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decoding [50.55024115943266]
  We introduce a novel semantic alignment method of multi-subject fMRI signals using so-called MindFormer. This model is specifically designed to generate fMRI-conditioned feature vectors that can be used for conditioning Stable Diffusion model for fMRI- to-image generation or large language model (LLM) for fMRI-to-text generation. Our experimental results demonstrate that MindFormer generates semantically consistent images and text across different subjects.
  arXiv  Detail & Related papers  (2024-05-28T00:36:25Z)
• Brain3D: Generating 3D Objects from fMRI [76.41771117405973]
  We design a novel 3D object representation learning method, Brain3D, that takes as input the fMRI data of a subject. We show that our model captures the distinct functionalities of each region of human vision system. Preliminary evaluations indicate that Brain3D can successfully identify the disordered brain regions in simulated scenarios.
  arXiv  Detail & Related papers  (2024-05-24T06:06:11Z)
• MindBridge: A Cross-Subject Brain Decoding Framework [60.58552697067837]
  Brain decoding aims to reconstruct stimuli from acquired brain signals. Currently, brain decoding is confined to a per-subject-per-model paradigm. We present MindBridge, that achieves cross-subject brain decoding by employing only one model.
  arXiv  Detail & Related papers  (2024-04-11T15:46:42Z)
• NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation [55.51412454263856]
  This paper proposes to directly modulate the generation process of diffusion models using fMRI signals. By training with about 67,000 fMRI-image pairs from various individuals, our model enjoys superior fMRI-to-image decoding capacity.
  arXiv  Detail & Related papers  (2024-03-27T02:42:52Z)
• NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties [23.893490180665996]
  We introduce NeuroCine, a novel dual-phase framework to targeting the inherent challenges of decoding fMRI data. tested on a publicly available fMRI dataset, our method shows promising results. Our attention analysis suggests that the model aligns with existing brain structures and functions, indicating its biological plausibility and interpretability.
  arXiv  Detail & Related papers  (2024-02-02T17:34:25Z)
• MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion [7.597218661195779]
  We propose a two-stage image reconstruction model called MindDiffuser. In Stage 1, the VQ-VAE latent representations and the CLIP text embeddings decoded from fMRI are put into Stable Diffusion. In Stage 2, we utilize the CLIP visual feature decoded from fMRI as supervisory information, and continually adjust the two feature vectors decoded in Stage 1 through backpagation to align the structural information.
  arXiv  Detail & Related papers  (2023-08-08T13:28:34Z)
• Joint fMRI Decoding and Encoding with Latent Embedding Alignment [77.66508125297754]
  We introduce a unified framework that addresses both fMRI decoding and encoding. Our model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.
  arXiv  Detail & Related papers  (2023-03-26T14:14:58Z)
• Natural scene reconstruction from fMRI signals using generative latent diffusion [1.90365714903665]
  We present a two-stage scene reconstruction framework called Brain-Diffuser'' In the first stage, we reconstruct images that capture low-level properties and overall layout using a VDVAE (Very Deep Vari Autoencoder) model. In the second stage, we use the image-to-image framework of a latent diffusion model conditioned on predicted multimodal (text and visual) features.
  arXiv  Detail & Related papers  (2023-03-09T15:24:26Z)
• Exploring Motion and Appearance Information for Temporal Sentence Grounding [52.01687915910648]
  We propose a Motion-Appearance Reasoning Network (MARN) to solve temporal sentence grounding. We develop separate motion and appearance branches to learn motion-guided and appearance-guided object relations. Our proposed MARN significantly outperforms previous state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2022-01-03T02:44:18Z)

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.