Research map / Image generation / Autoregressive and latent generation
Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN
Tao Fang, Yu Qi, Gang Pan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add semantic features (semantic decoder plus U-Net generator) instead of shape-only pix2pix (ablation) | Shape-Semantic GAN · fMRI image reconstruction | pairwise SSIM similarity (%): 62.5 -> 65.3 | Improved |
| add ImageNet data augmentation (about 1.2k images) in GAN training (ablation) | Shape-Semantic GAN · fMRI image reconstruction | pairwise SSIM similarity (%): 63.6 -> 65.3 | Improved |
| decode semantics from HVC instead of LVC (ablation) | semantic decoder · 10-category identification | identification accuracy: by 14.5\% | Improved |
| decode shapes from LVC instead of HVC (ablation) | shape decoder · shape decoding | pairwise SSIM similarity: by 19.3\% | Improved |
| train decoders on whole visual cortex instead of LVC/HVC specific areas (ablation) | shape and semantic decoders · shape/semantic decoding | decoding performance | Hurt |
| compare against prior reconstruction methods | Shape-Semantic GAN · fMRI image reconstruction | pairwise SSIM similarity (%): 64.3 -> 65.3 | Improved |
Closest papers by meaning
- Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs (ICLR 2021 · similarity 0.87)
- Mind Reader: Reconstructing complex images from brain activities (NeurIPS 2022 · similarity 0.86)
- MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activity (NeurIPS 2024 · similarity 0.85)
- MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding (NeurIPS 2025 · similarity 0.85)
- Multigranular Evaluation for Brain Visual Decoding (AAAI 2026 · similarity 0.84)
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
