Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911579498348544 |
|---|---|
| author | Hyoseok, Lee Lim, Sohwi Cha, Eunju Oh, Tae-Hyun |
| author_facet | Hyoseok, Lee Lim, Sohwi Cha, Eunju Oh, Tae-Hyun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04791 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers Hyoseok, Lee Lim, Sohwi Cha, Eunju Oh, Tae-Hyun Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2601.04791 |