通过动态剪枝与运动感知，实现局部运动去模糊的高效计算。
Motion-Aware Adaptive Pixel Pruning for Efficient Local Motion Deblurring
- 训练可学习掩码预测器定位模糊区域，推理时剪枝清晰像素以降算力。
- 利用帧内运动分析生成自适应引导，精准恢复不同区域的模糊模式。
- 在保持高精度的同时减少49%计算量，适合移动端实时去模糊应用。
数字图像中的局部运动模糊源于动态物体与静态成像系统在曝光期间的相对运动。现有去模糊方法因计算资源分配效率低、难以处理空间变化的模糊模式而面临挑战。本文提出可训练的掩码预测器，通过模糊掩码在训练中排除清晰区域；推理时采用结构重参数化，将3×3卷积转为1×1卷积，实现像素级剪枝以降低计算开销。同时设计帧内运动分析器，将像素位移转换为运动轨迹，提供区域自适应的去模糊指导。模型采用重建损失、重模糊损失和掩码损失联合训练，使用标注模糊掩码进行监督。大量实验表明，在局部与全局模糊数据集上均优于当前最优方法，且相比SOTA模型（如LMD-ViT）减少49%浮点运算量（FLOPs）。源代码已开源：https://github.com/shangwei5/M2AENet。
原文摘要 · Abstract (English)
Local motion blur in digital images originates from the relative motion between dynamic objects and static imaging systems during exposure. Existing deblurring methods face significant challenges in addressing this problem due to their inefficient allocation of computational resources and inadequate handling of spatially varying blur patterns. To overcome these limitations, we first propose a trainable mask predictor that identifies blurred regions in the image. During training, we employ blur masks to exclude sharp regions. For inference optimization, we implement structural reparameterization by converting $3\times 3$ convolutions to computationally efficient $1\times 1$ convolutions, enabling pixel-level pruning of sharp areas to reduce computation. Second, we develop an intra-frame motion analyzer that translates relative pixel displacements into motion trajectories, establishing adaptive guidance for region-specific blur restoration. Our method is trained end-to-end using a combination of reconstruction loss, reblur loss, and mask loss guided by annotated blur masks. Extensive experiments demonstrate superior performance over state-of-the-art methods on both local and global blur datasets while reducing FLOPs by 49\% compared to SOTA models (e.g., LMD-ViT). The source code is available at https://github.com/shangwei5/M2AENet.
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。