用频域信息提升模糊核估计，让模糊图像恢复更清晰。
Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring
- 引入频域特征增强模糊核建模的结构可辨识性
- 在严重模糊区域仍保持准确的核估计性能
- 适合需要高精度图像复原的视觉任务
单图像散焦去模糊旨在从模糊图像中恢复全聚焦图像，其中准确建模空间变化的模糊核仍是关键挑战。现有方法多依赖空间特征进行核估计，但在局部高频细节缺失的严重模糊区域性能下降。为此，我们提出频率驱动的逆核预测网络（FDIKP），引入频域表示以增强核建模中的结构可辨识性。鉴于频域在模糊建模中的优异区分能力，设计双分支逆核预测（DIKP）策略，在提升核估计精度的同时保持稳定性。针对预测逆核数量有限的问题，引入位置自适应卷积（PAC）以增强去卷积过程的适应性。最后，提出双域尺度递归模块（DSRM），融合去卷积结果并实现从粗到细的渐进式去模糊质量提升。大量实验表明，本方法优于现有方法。代码将公开。
原文摘要 · Abstract (English)
Single image defocus deblurring aims to recover an all-in-focus image from a defocus counterpart, where accurately modeling spatially varying blur kernels remains a key challenge. Most existing methods rely on spatial features for kernel estimation, but their performance degrades in severely blurry regions where local high-frequency details are missing. To address this, we propose a Frequency-Driven Inverse Kernel Prediction network (FDIKP) that incorporates frequency-domain representations to enhance structural identifiability in kernel modeling. Given the superior discriminative capability of the frequency domain for blur modeling, we design a Dual-Branch Inverse Kernel Prediction (DIKP) strategy that improves the accuracy of kernel estimation while maintaining stability. Moreover, considering the limited number of predicted inverse kernels, we introduce a Position Adaptive Convolution (PAC) to enhance the adaptability of the deconvolution process. Finally, we propose a Dual-Domain Scale Recurrent Module (DSRM) to fuse deconvolution results and progressively improve deblurring quality from coarse to fine. Extensive experiments demonstrate that our method outperforms existing approaches. Code will be made publicly available.
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。