[2601.04791] Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers

Computer Science > Computer Vision and Pattern Recognition arXiv:2601.04791 (cs) [Submitted on 8 Jan 2026 (v1), last revised 4 Mar 2026 (this version, v2)] Title:Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers Authors:Lee Hyoseok, Sohwi Lim, Eunju Cha, Tae-Hyun Oh View a PDF of the paper titled Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers, by Lee Hyoseok and 3 other authors View PDF Abstract:While latent diffusion models (LDMs) have emerged as powerful priors for inverse problems, existing LDM-based solvers frequently suffer from instability. In this work, we first identify the instability as a discrepancy between the solver dynamics and stable reverse diffusion dynamics learned by the diffusion model, and show that reducing this gap stabilizes the solver. Building on this, we introduce \textit{Measurement-Consistent Langevin Corrector (MCLC)}, a theoretically grounded plug-and-play stabilization module that remedies the LDM-based inverse problem solvers through measurement-consistent Langevin updates. Compared to prior approaches that rely on linear manifold assumptions, which often fail to hold in latent space, MCLC provides a principled stabilization mechanism, leading to more stable and reliable behavior in latent space. Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) Cite as: arXiv:2601.04791 [cs.CV]   (or arXiv:2601.04...