Metraipolis › archive › dc_9b64e6c8d0dc
FFAI: Flow Matching with Feedback Training and Adaptive Initialization for CT Reconstruction — arXiv:2610.39517
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39517
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:42:00.315Z
- SHA-256 of the archived text
b6e65aa75e22a85abf7bf6d0cbfd0bac33d8eeaeaa3f1db141f370b89d8222e4- Stable URL of this page
https://metraipolis.com/documento/dc_9b64e6c8d0dc
How to cite
FFAI: Flow Matching with Feedback Training and Adaptive Initialization for CT Reconstruction — arXiv:2610.39517 — arXiv (en), https://arxiv.org/abs/2610.39517 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9b64e6c8d0dc (Metraipolis archive dc_9b64e6c8d0dc, sha256 b6e65aa75e22a85abf7bf6d0cbfd0bac33d8eeaeaa3f1db141f370b89d8222e4)
BibTeX
@misc{dc9b64e6c8d0dc,
title = {FFAI: Flow Matching with Feedback Training and Adaptive Initialization for CT Reconstruction — arXiv:2610.39517},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39517},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9b64e6c8d0dc; sha256 b6e65aa75e22a85abf7bf6d0cbfd0bac33d8eeaeaa3f1db141f370b89d8222e4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39517. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Although low-dose, sparse-view, and limited-angle CT involve distinct degradation mechanisms, all three pose reconstruction challenges due to limited measurement information and can therefore be addressed within a unified framework. In iterative image restoration with flow matching, prediction errors may cause inference states to deviate from the prescribed training path, while a fixed initialization may be unsuitable for inputs with varying degradation severity. We propose a unified conditional flow matching method that conditions on the initial reconstruction and combines feedback-aware training with degradation-adaptive initialization. During training, a teacher network simulates inference updates to generate shifted states, from which a student network learns to recover high-quality reference images, improving its ability to handle prediction errors. During inference, the starting time is selected based on the noise level or extent of missing projection data, and the noise added to the initial state is adjusted accordingly to adapt the starting point to the input. Experiments on public benchmark datasets show that the proposed method achieves better quantitative results than the compared methods across all three reconstruction tasks, effectively suppressing noise and artifacts while preserving anatomical structures and details. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.39517 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-01T02:16:43.932Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).