Multi-Scene Separation and Reconstruction From the Fused Random Compressed Measurements

Compressive sensing (CS) has revolutionized image acquisition and reconstruction; however, its primary application has been in the domain of single-sence image processing. This study introduces a novel approach that extends CS frameworks to multi-scene settings, enabling the efficient separation and reconstruction of multiple distinct scenes from fused random measurements. The key innovation lies in the theoretical derivation of the momentum weight structure for cross-scene fusion, which is proven to be the sum of divergences from two proximal mapping processes. The proposed method deconstructs the multi-scene CS challenge into multiple sub-optimization tasks with interconnected message passing, where each scene’s reconstruction is solved using an iterative alternating-minimization / block-coordinate descent scheme. Our multi-scene approach enables multiple sensors to share a single transmission channel, balancing the reconstruction quality across multiple scenes. The experimental results demonstrate that our multi-scene compressed sensing framework, integrated with an efficient deep image denoiser as the proximal operator, achieves superior reconstruction quality. The test code is available at