在角度信息模糊时，用多阶段细化恢复旋转运动模糊图像。
CAR-Net: A Cascade Refinement Network for Rotational Motion Deblurring under Angle Information Uncertainty
- 从频域反演得初版去模糊图像，逐级修正残差。
- 在真实与合成数据上均有效，可处理角度噪声。
- 适合图像恢复、自动驾驶等需鲁棒去模糊的场景。
我们提出一种名为CAR-net（Cascade Refinement Network）的新型神经网络架构，用于去除受旋转运动模糊影响的图像。该架构专为半盲场景设计，即仅能获得旋转模糊角度的噪声信息。核心思路是通过渐进式细化过程：先基于频域反演得到初始去模糊估计，再经一系列细化阶段，利用当前去模糊图像预测并施加残差修正，逐步抑制伪影并恢复细节。为应对参数不确定性，模型支持可端到端训练的角度检测模块。通过合成与真实图像实验验证了方法的有效性。代码、模型及数据集链接见https://github.com/tony123105/CAR-Net。
原文摘要 · Abstract (English)
We propose a new neural network architecture called CAR-net (CAscade Refinement Network) to deblur images that are subject to rotational motion blur. Our architecture is specifically designed for the semi-blind scenarios where only noisy information of the rotational motion blur angle is available. The core of our approach is progressive refinement process that starts with an initial deblurred estimate obtained from frequency-domain inversion; A series of refinement stages take the current deblurred image to predict and apply residual correction to the current estimate, progressively suppressing artifacts and restoring fine details. To handle parameter uncertainty, our architecture accommodates an optional angle detection module which can be trained end-to-end with refinement modules. We provide a detailed description of our architecture and illustrate its efficiency through experiments using both synthetic and real-life images. Our code and model as well as the links to the datasets are available at https://github.com/tony123105/CAR-Net
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。