AI 中文总结
该研究针对实际 CASSI 系统中 PSF 导致的问题，提出深度展开框架。通过共轭梯度展开、梯度细化模块、PSF 条件惩罚估计器及蒙特卡罗 PSF 训练策略解决算法挑战，在 KAIST 数据集上取得良好重建效果，性能优于基线。
AI 中文摘要
深度展开方法在编码孔径快照光谱成像（CASSI）重建中取得了先进性能，但通常依赖假设理想光学系统的闭式数据保真度更新。在实际 CASSI 系统中，场依赖和波长依赖的点扩散函数（PSF）引入卷积耦合，破坏了正规方程的对角结构，使闭式更新不适用。我们提出一个深度展开框架，通过三项贡献解决这一算法挑战：一是 $K$ 步共轭梯度（CG）展开，在包含 PSF 的前向算子下显式求解非对角正规方程；二是基于每个波长的 PSF 嵌入生成波长自适应步长的梯度细化模块；三是使 ADMM 正则化强度适应光学退化严重程度的 PSF 条件惩罚估计器。蒙特卡罗 PSF 训练策略进一步提高对制造引起的 PSF 变化的鲁棒性。我们的方法在 KAIST 数据集上达到 30.53dB，使用可比数量参数（1.42M）比 DPU 基线（1.27M）高 2.73dB，使用少 33%参数比更大基线（DPU-B+，2.12M）高 1.70dB。
英文摘要
Deep unfolding methods achieve state-of-the-art performance in coded aperture snapshot spectral imaging (CASSI) reconstruction but typically rely on closed-form data-fidelity updates that assume an ideal optical system. In practical CASSI systems, the field-dependent and wavelength-dependent point spread function (PSF) introduces convolutional coupling that breaks the diagonal structure of the normal equation, rendering closed-form updates inapplicable. We propose a deep unfolding framework that addresses this fundamental algorithmic challenge through three contributions: (1)~a $K$-step conjugate gradient (CG) unrolling that explicitly solves the non-diagonal normal equation under PSF-inclusive forward operators; (2)~a learned gradient refinement module with wavelength-adaptive step sizes generated from a per-wavelength PSF embedding; and (3)~a PSF-conditioned penalty estimator that adapts the ADMM regularization strength to the optical degradation severity. A Monte Carlo PSF training strategy further improves robustness to manufacturing-induced PSF variations. Our method achieves 30.53~dB on the KAIST dataset, +2.73~dB over the DPU baseline (1.27M) using a comparable number of parameters (1.42M), and +1.70~dB over a larger baseline (DPU-B+, 2.12M) using 33\% fewer parameters.
