{"ID":2868316,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16509","arxiv_id":"2509.16509","title":"SlowFast-SCI: Slow-Fast Deep Unfolding Learning for Spectral Compressive Imaging","abstract":"Humans learn in two complementary ways: a slow, cumulative process that builds broad, general knowledge, and a fast, on-the-fly process that captures specific experiences. Existing deep-unfolding methods for spectral compressive imaging (SCI) mirror only the slow component-relying on heavy pre-training with many unfolding stages-yet they lack the rapid adaptation needed to handle new optical configurations. As a result, they falter on out-of-distribution cameras, especially in bespoke spectral setups unseen during training. This depth also incurs heavy computation and slow inference. To bridge this gap, we introduce SlowFast-SCI, a dual-speed framework seamlessly integrated into any deep unfolding network beyond SCI systems. During slow learning, we pre-train or reuse a priors-based backbone and distill it via imaging guidance into a compact fast-unfolding model. In the fast learning stage, lightweight adaptation modules are embedded within each block and trained self-supervised at test time via a dual-domain loss-without retraining the backbone. To the best of our knowledge, SlowFast-SCI is the first test-time adaptation-driven deep unfolding framework for efficient, self-adaptive spectral reconstruction. Its dual-stage design unites offline robustness with on-the-fly per-sample calibration-yielding over 70% reduction in parameters and FLOPs, up to 5.79 dB PSNR improvement on out-of-distribution data, preserved cross-domain adaptability, and a 4x faster adaptation speed. In addition, its modularity integrates with any deep-unfolding network, paving the way for self-adaptive, field-deployable imaging and expanded computational imaging modalities. The models, datasets, and code are available at https://github.com/XuanLu11/SlowFast-SCI.","short_abstract":"Humans learn in two complementary ways: a slow, cumulative process that builds broad, general knowledge, and a fast, on-the-fly process that captures specific experiences. Existing deep-unfolding methods for spectral compressive imaging (SCI) mirror only the slow component-relying on heavy pre-training with many unfold...","url_abs":"https://arxiv.org/abs/2509.16509","url_pdf":"https://arxiv.org/pdf/2509.16509v2","authors":"[\"Haijin Zeng\",\"Xuan Lu\",\"Yurong Zhang\",\"Qiangqiang Shen\",\"Guoqing Chao\",\"Li Jiang\",\"Yongyong Chen\"]","published":"2025-09-20T03:09:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609571,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2868316,"paper_url":"https://arxiv.org/abs/2509.16509","paper_title":"SlowFast-SCI: Slow-Fast Deep Unfolding Learning for Spectral Compressive Imaging","repo_url":"https://github.com/XuanLu11/SlowFast-SCI","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}