Visual Image Reconstruction from Brain Activity via Latent Representation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915351764140032 |
|---|---|
| author | Kamitani, Yukiyasu Tanaka, Misato Shirakawa, Ken |
| author_facet | Kamitani, Yukiyasu Tanaka, Misato Shirakawa, Ken |
| contents | Visual image reconstruction, the decoding of perceptual content from brain activity into images, has advanced significantly with the integration of deep neural networks (DNNs) and generative models. This review traces the field's evolution from early classification approaches to sophisticated reconstructions that capture detailed, subjective visual experiences, emphasizing the roles of hierarchical latent representations, compositional strategies, and modular architectures. Despite notable progress, challenges remain, such as achieving true zero-shot generalization for unseen images and accurately modeling the complex, subjective aspects of perception. We discuss the need for diverse datasets, refined evaluation metrics aligned with human perceptual judgments, and compositional representations that strengthen model robustness and generalizability. Ethical issues, including privacy, consent, and potential misuse, are underscored as critical considerations for responsible development. Visual image reconstruction offers promising insights into neural coding and enables new psychological measurements of visual experiences, with applications spanning clinical diagnostics and brain-machine interfaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08429 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Visual Image Reconstruction from Brain Activity via Latent Representation Kamitani, Yukiyasu Tanaka, Misato Shirakawa, Ken Computer Vision and Pattern Recognition Neurons and Cognition Visual image reconstruction, the decoding of perceptual content from brain activity into images, has advanced significantly with the integration of deep neural networks (DNNs) and generative models. This review traces the field's evolution from early classification approaches to sophisticated reconstructions that capture detailed, subjective visual experiences, emphasizing the roles of hierarchical latent representations, compositional strategies, and modular architectures. Despite notable progress, challenges remain, such as achieving true zero-shot generalization for unseen images and accurately modeling the complex, subjective aspects of perception. We discuss the need for diverse datasets, refined evaluation metrics aligned with human perceptual judgments, and compositional representations that strengthen model robustness and generalizability. Ethical issues, including privacy, consent, and potential misuse, are underscored as critical considerations for responsible development. Visual image reconstruction offers promising insights into neural coding and enables new psychological measurements of visual experiences, with applications spanning clinical diagnostics and brain-machine interfaces. |
| title | Visual Image Reconstruction from Brain Activity via Latent Representation |
| topic | Computer Vision and Pattern Recognition Neurons and Cognition |
| url | https://arxiv.org/abs/2505.08429 |