用深度先验和可缩放等变性，提升低噪声下高动态范围模成像的重建质量。
Deep Lightweight Unrolled Network for High Dynamic Range Modulo Imaging
- 将重建问题建模为带深度先验的优化问题，并展开为神经网络
- 在高噪声场景下仍能有效恢复图像，且推理速度快、计算开销小
- 支持自监督微调，适配未见过的模成像数据分布
模成像（Modulo-Imaging, MI）通过在信号饱和时重置强度，为扩展图像动态范围提供了一种有前景的方案。然而，高动态范围（HDR）模成像需要恢复过程，该问题具有非凸性和病态性，现有恢复网络在高噪声环境下表现不佳。本文将HDR重建任务建模为包含深度先验的优化问题，并将其展开为基于优化思想的深度神经网络。网络采用轻量级卷积去噪器，实现快速推理且计算开销极低，有效恢复强度值并抑制噪声。此外，提出缩放等变性项，支持自监督微调，使模型能适应超出原始训练分布的新模成像数据。大量实验表明，本方法在性能与图像质量上均优于当前最优算法。
原文摘要 · Abstract (English)
Modulo-Imaging (MI) offers a promising alternative for expanding the dynamic range of images by resetting the signal intensity when it reaches the saturation level. Subsequently, high-dynamic range (HDR) modulo imaging requires a recovery process to obtain the HDR image. MI is a non-convex and ill-posed problem where recent recovery networks suffer in high-noise scenarios. In this work, we formulate the HDR reconstruction task as an optimization problem that incorporates a deep prior and subsequently unrolls it into an optimization-inspired deep neural network. The network employs a lightweight convolutional denoiser for fast inference with minimal computational overhead, effectively recovering intensity values while mitigating noise. Moreover, we introduce the Scaling Equivariance term that facilitates self-supervised fine-tuning, thereby enabling the model to adapt to new modulo images that fall outside the original training distribution. Extensive evaluations demonstrate the superiority of our method compared to state-of-the-art recovery algorithms in terms of performance and quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。