Fluorescence molecular tomography (FMT) can non-invasively monitor glioblastomas in small animals. Both handcrafted priors regularization and deep learning algorithms have made remarkable achievements in this field. But handcrafted priors often can’t deal well with different kinds of tumors. Also, some deep learning methods still rely on handcrafted priors. In this paper, we introduce a Chebyshev Non-explicit Prior Regularizer Network (CNPRN). It replaces hand-crafted prior with a non-explicit prior and combines with an optimization-inspired net work. CNPRN has two main parts: First, because of the long-range spatial correlation of light transmission in the finite element mesh, we create a non-explicit prior regularizer using high-order Chebyshev graph convo lution. We also add inter-stage information pathways to combine useful data from the reconstructed outputs of each phase’s regularizer. Second, to solve the problem of heavy computation in iterative optimization and make the network more flexible, introduce a dynamic gradient descent module. This module allows parameters to be adjusted adaptively. As a deep unrolling method, CNPRN naturally gets the solution constraints of the Half Quadratic Splitting method. This improves the network’s generalizability and stability. Both simulation and in-vivo experiments indicated that CNPRN has superior reconstruction performance.