Pseudo-Invertible Neural Networks

arXiv:2602.06042v2 Announce Type: replace-cross Abstract: The Moore-Penrose Pseudo-inverse (PInv) serves as the fundamental solution for linear systems. In this paper, we propose a natural generalization of PInv to the nonlinear regime in general and to neural networks in particular. We introduce Surjective Pseudo-invertible Neural Networks (SPNN), a class of architectures explicitly designed to admit a tractable non-linear PInv. The proposed non-linear PInv and its implementation in SPNN satisfy fundamental geometric properties. One such property is null-space projection or "Back-Projection", x' = x + A^agger(y-Ax), which moves a sample x to its closest consistent state x' satisfying Ax=y. We formalize Non-Linear Back-Projection (NLBP), a method that guarantees the same consistency constraint for non-linear mappings f(x)=y via our defined PInv. We leverage SPNNs to expand the scope of zero-shot inverse problems. Diffusion-based null-space projection has revolutionized zero-shot solving for linear inverse problems by exploiting closed-form back-projection. We extend this method to non-linear degradations. Here, "degradation" is broadly generalized to include any non-linear loss of information, spanning from optical distortions to semantic abstractions like classification. This approach enables zero-shot inversion of complex degradations and allows precise semantic control over generative outputs without retraining the diffusion prior.

Related

• Efficient Cross-Scale Invertible Hiding Network with Spatial-Frequency Collaboration and Non-Invertible Mechanism
• Examining the robustness of Physics-Informed Neural Networks to noise for Inverse Problems
• An analytic theory of convolutional neural network inverse problems solvers
• Iskra: A System for Inverse Geometry Processing

Source: arXiv cs.CV | 2026-09-28