2025/05/21 by Jorge Bacca, Bacca, Jorge
Computer Science · #Advanced Image and Video Retrieval Techniques #Computational Physics (physics.comp-ph) #Computer Vision and Pattern Recognition (cs.CV) #Consistency (knowledge bases) #FOS: Computer and information sciences #FOS: Physical sciences #Generalized inverse #Handwritten Text Recognition Techniques #Inference #Inverse #Inverse problem #Machine Learning (cs.LG) #NASA Deep Space Network #Neural Networks and Applications #Projection (relational algebra)
paper · pdf · doi:10.48550/arxiv.2505.15777
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/05/21 · openalex created_date 2025/10/19 · openalex updated_date 2026/08/05
Deep learning-based models have demonstrated remarkable success in solving illposed inverse problems; however, many fail to strictly adhere to the physical constraints imposed by the measurement process. In this work, we introduce a projection-based correction method to enhance the inference of deep inverse networks by ensuring consistency with the forward model. Specifically, given an initial estimate from a learned reconstruction network, we apply a projection step that constrains the solution to lie within the valid solution space of the inverse problem. We theoretically demonstrate that if the recovery model is a well-trained deep inverse network, the solution can be decomposed into range-space and null-space components, where the projection-based correction reduces to an identity transformation. Extensive simulations and experiments validate the proposed method, demonstrating improved reconstruction accuracy across diverse inverse problems and deep network architectures.