用提示词设计采样策略，提升图像压缩感知恢复效果
Active Learning for Conditional Generative Compressed Sensing
- 用提示词控制采样分布，实现条件生成压缩感知
- 提示匹配时恢复误差与最优理论一致，不匹配则有兼容性惩罚
- 适用于需精准控制生成图像的科研或工业场景
生成式压缩感知利用预训练生成器的输出空间作为结构信号的非线性模型，从有限测量中恢复信号。本文研究基于提示词的图像恢复问题，使用子采样傅里叶测量和提示条件生成模型。框架区分了两种条件作用：用于设计采样分布的提示与用于定义恢复模型的提示。针对ReLU和Lipschitz条件生成器，我们证明了稳定恢复界：提示匹配时，克里斯托弗尔采样保留与现有近似最优生成式压缩感知理论相同的克里斯托弗尔复杂度常数；提示不匹配则引入明确的兼容性惩罚。在Stable Diffusion上的实验表明，提示能显著改变克里斯托弗尔采样分布并影响图像恢复质量。总体而言，结果表明提示应被视为具有不同影响的可设计变量，分别作用于传感、逼近与恢复。
原文摘要 · Abstract (English)
Generative compressed sensing uses the range of a pretrained generator as a nonlinear model for recovering structured signals from limited measurements. We study a conditional version of this problem for image recovery from subsampled Fourier measurements using prompt-conditioned generative models. Our framework separates two roles of conditioning: the prompt used to design the sampling distribution and the prompt used to define the recovery model. For ReLU and Lipschitz conditional generators, we prove stable recovery bounds showing that prompt-matched Christoffel sampling retains the same Christoffel complexity constant as existing near-optimal generative compressed sensing theory, while prompt mismatch incurs an explicit compatibility penalty. Experiments with Stable Diffusion show that prompts meaningfully reshape Christoffel sampling distributions and influence image recovery. Overall, our results suggest that prompts should be treated as design variables with distinct effects on sensing, approximation, and recovery.
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。