首个跨模态压缩成像误差评估基准，揭示模型对物理参数失配的脆弱性。
InverseNet: Benchmarking Operator Mismatch and Calibration Across Compressive Imaging Modalities
- 构建跨模态基准，测试不同成像系统在参数失配下的表现。
- 深度学习方法在失配下性能下降10-21 dB，优势消失。
- 仅依赖物理先验的模型可恢复90%以上损失，适合实际部署。
当前最先进的高效压缩感知成像（EfficientSCI）在仅8个参数偏离真实物理模型时，性能下降20.58 dB，但现有基准无法量化这种参数失配——而这正是部署系统中的默认状态。本文提出Inversenet，首个跨模态的参数失配基准，涵盖CASSI、CACTI和单像素相机三种成像系统。在27个仿真场景与9组真实硬件数据上，采用四类情景协议（理想、失配、真值修正、盲校准）评估12种方法。结果表明：(1) 深度学习方法在失配条件下性能损失10-21 dB，丧失对传统方法的优势；(2) 各模态间性能与鲁棒性呈显著负相关（Spearman r_s = -0.71, p < 0.01）；(3) 无掩码感知架构无法恢复任何失配损失（0%），而基于操作符条件化的模型可恢复41%-90%；(4) 盲网格搜索校准可恢复85%-100%的真值边界，无需真实标签。真实硬件实验验证了仿真趋势在物理数据中的可迁移性。代码将在论文接收后公开。
原文摘要 · Abstract (English)
State-of-the-art EfficientSCI loses 20.58 dB when its assumed forward operator deviates from physical reality in just eight parameters, yet no existing benchmark quantifies operator mismatch, the default condition in deployed compressive imaging systems. We introduce InverseNet, the first cross-modality benchmark for operator mismatch, spanning CASSI, CACTI, and single-pixel cameras. Evaluating 12 methods under a four-scenario protocol (ideal, mismatched, oracle-corrected, blind calibration) across 27 simulated scenes and 9 real hardware captures, we find: (1) deep learning methods lose 10-21 dB under mismatch, eliminating their advantage over classical baselines; (2) performance and robustness are inversely correlated across modalities (Spearman r_s = -0.71, p < 0.01); (3) mask-oblivious architectures recover 0% of mismatch losses regardless of calibration quality, while operator-conditioned methods recover 41-90%; (4) blind grid-search calibration recovers 85-100% of the oracle bound without ground truth. Real hardware experiments confirm that simulation trends transfer to physical data. Code will be released upon acceptance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。