Resolving Blind Inverse Problems under Dynamic Range Compression via Structured Forward Operator Modeling

TL;DR

This paper introduces CaMB-Diff, a novel framework combining a physically grounded operator model and diffusion priors to recover radiometric fidelity in unknown dynamic range compression tasks, outperforming existing methods.

Contribution

The paper proposes the CaMB operator for physically consistent forward modeling and integrates it with diffusion models for robust blind inverse problem solving.

Findings

CaMB-Diff outperforms state-of-the-art zero-shot methods in various UDRC tasks.

The CaMB parameterization accurately models unknown forward operators.

The framework ensures physical consistency and stable operator estimation.

Abstract

Recovering radiometric fidelity from unknown dynamic range compression (UDRC), such as low-light enhancement and HDR reconstruction, is a challenging blind inverse problem, due to the unknown forward model and irreversible information loss introduced by compression. To address this challenge, we first identify monotonicity as the fundamental physical invariant shared across UDRC tasks. Leveraging this insight, we introduce the \textbf{cascaded monotonic Bernstein} (CaMB) operator to parameterize the unknown forward model. CaMB enforces monotonicity as a hard architectural inductive bias, constraining optimization to physically consistent mappings and enabling robust and stable operator estimation. We further integrate CaMB with a plug-and-play diffusion framework, proposing \textbf{CaMB-Diff}. Within this framework, the diffusion model serves as a powerful geometric prior for structural and semantic recovery, while CaMB explicitly models and corrects radiometric distortions through a physically grounded forward operator. Extensive experiments on a variety of zero-shot UDRC tasks, including low-light enhancement, low-field MRI enhancement, and HDR reconstruction, demonstrate that CaMB-Diff significantly outperforms state-of-the-art zero-shot baselines in terms of both signal fidelity and physical consistency. Moreover, we empirically validate the effectiveness of the proposed CaMB parameterization in accurately modeling the unknown forward operator.