Deep Probabilistic Unfolding for Quantized Compressive Sensing
It addresses the accuracy-efficiency trade-off in quantized compressive sensing for signal reconstruction applications.
The paper proposes a deep probabilistic unfolding model for quantized compressive sensing that uses a closed-form likelihood gradient projection to respect quantization physics and a dual-domain Mamba module for multi-scale feature fusion, achieving state-of-the-art reconstruction accuracy and efficiency.
We propose a deep probabilistic unfolding model to address the classical quantized compressive sensing problem that leverages an unfolding framework to enhance the reconstruction accuracy and efficiency. Unlike previous unfolding methods that apply L2 projection to measurements, we derive a closed-form, numerically stable likelihood gradient projection, which allows the model to respect the true quantization physics, turning the hard quantization constraint into a soft probabilistic guidance. Furthermore, an efficient, dual-domain Mamba module is specifically designed to dynamically capture and fuse the multi-scale local and global features, ensuring the interactions between the distant but correlated regions. Extensive experiments demonstrate the state-of-the-art performance of the proposed method over previous works, which is capable of promoting the application of quantized compressive sensing in real life.