We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| facebookresearch/dynadiff | canonical | 4 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| batch_intersection_union | Ran | facebookresearch/dynadiff/metrics/mIOU/eval_miou.py pointer only (licence: MIT) · get_code("d09bf6c7c12f65f3") |
| batch_pix_accuracy | Ran | facebookresearch/dynadiff/metrics/mIOU/eval_miou.py pointer only (licence: MIT) · get_code("f1fb897b7787acfa") |
| get_mask | Ran | facebookresearch/dynadiff/blur.py pointer only (licence: MIT) · get_code("bd3ca5bbe94ef235") |
| intersectionAndUnion | Ran | facebookresearch/dynadiff/metrics/mIOU/eval_miou.py pointer only (licence: MIT) · get_code("de2ee01cea02bf0f") |
| compute_miou | Not yet run | facebookresearch/dynadiff/metrics/mIOU/evaluate_img_gen.py pointer only (licence: MIT) · get_code("02015a2dbd02c1de") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Brain-to-image decoding has been recently propelled by the progress in generative AI models and the availability of large ultra-high field functional Magnetic Resonance Imaging (fMRI). However, current approaches depend on complicated multi-stage pipelines and preprocessing steps that typically collapse the temporal dimension of brain recordings, thereby limiting time-resolved brain decoders. Here, we introduce Dynadiff (Dynamic Neural Activity Diffusion for Image Reconstruction), a new single-stage diffusion model designed for reconstructing images from dynamically evolving fMRI recordings. Our approach offers three main contributions. First, Dynadiff simplifies training as compared to existing approaches. Second, our model outperforms state-of-the-art models on time-resolved fMRI signals, especially on high-level semantic image reconstruction metrics, while remaining competitive on preprocessed fMRI data that collapse time. Third, this approach allows a precise characterization of the evolution of image representations in brain activity. Overall, this work lays the foundation for time-resolved brain-to-image decoding.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2505.14556")
get_code_for_paper("2505.14556")
have("2505.14556")
Connect an agent — have() is free.