VmambaIR：用于图像恢复的视觉状态空间模型
VmambaIR: Visual State Space Model for Image Restoration
AI总结：
VmambaIR提出基于状态空间模型的图像恢复框架，利用全向选择性扫描和高效前馈网络，在多个任务上以更低计算量实现SOTA性能。
摘要：
图像恢复是低级计算机视觉中的一项关键任务，旨在从退化输入中恢复出高质量图像。各种模型，如卷积神经网络（CNNs）、生成对抗网络（GANs）、Transformer和扩散模型（DMs），已被用于解决这一问题并产生了显著影响。然而，CNNs在捕捉长距离依赖方面存在局限性。DMs需要大型先验模型和计算密集的去噪步骤。Transformer具有强大的建模能力，但面临输入图像尺寸二次复杂度的挑战。为解决这些挑战，我们提出了VmambaIR，它将具有线性复杂度的状态空间模型（SSMs）引入到全面的图像恢复任务中。我们利用Unet架构来堆叠我们提出的全向选择性扫描（OSS）块，该块由一个OSS模块和一个高效前馈网络（EFFN）组成。我们提出的全向选择性扫描机制通过高效地建模所有六个方向上的图像信息流，克服了SSMs单向建模的局限性。此外，我们在多个图像恢复任务中对我们的VmambaIR进行了全面评估，包括图像去雨、单图像超分辨率和真实世界图像超分辨率。大量实验结果表明，我们提出的VmambaIR以更少的计算资源和参数实现了最先进的（SOTA）性能。我们的研究强调了状态空间模型作为Transformer和CNN架构的有前途替代方案，在作为下一代低级视觉任务的基础框架方面的潜力。
英文摘要：
Image restoration is a critical task in low-level computer vision, aiming to restore high-quality images from degraded inputs. Various models, such as convolutional neural networks (CNNs), generative adversarial networks (GANs), transformers, and diffusion models (DMs), have been employed to address this problem with significant impact. However, CNNs have limitations in capturing long-range dependencies. DMs require large prior models and computationally intensive denoising steps. Transformers have powerful modeling capabilities but face challenges due to quadratic complexity with input image size. To address these challenges, we propose VmambaIR, which introduces State Space Models (SSMs) with linear complexity into comprehensive image restoration tasks. We utilize a Unet architecture to stack our proposed Omni Selective Scan (OSS) blocks, consisting of an OSS module and an Efficient Feed-Forward Network (EFFN). Our proposed omni selective scan mechanism overcomes the unidirectional modeling limitation of SSMs by efficiently modeling image information flows in all six directions. Furthermore, we conducted a comprehensive evaluation of our VmambaIR across multiple image restoration tasks, including image deraining, single image super-resolution, and real-world image super-resolution. Extensive experimental results demonstrate that our proposed VmambaIR achieves state-of-the-art (SOTA) performance with much fewer computational resources and parameters. Our research highlights the potential of state space models as promising alternatives to the transformer and CNN architectures in serving as foundational frameworks for next-generation low-level visual tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
