动态预测高通核，高效恢复视频模糊中的细节。
Adaptive High-Pass Kernel Prediction for Efficient Video Deblurring
- 通过线性组合基核动态生成自适应高通核，提取高频特征。
- 在低内存开销下实现更快推理速度，性能超越同类轻量模型。
- 适合需要实时去模糊且资源受限的视频处理场景。
当前先进的视频去模糊方法依赖深度网络架构恢复清晰帧。模糊会严重损害高频信息，但近期模型多关注架构设计而忽视此问题。由于神经网络存在谱偏差（倾向于学习低频函数），恢复细节尤为困难。为此，我们引入显式网络结构以捕捉精细纹理与边缘。通过线性组合一组高通基核，动态预测自适应高通核，以提取高频特征。该策略高度高效，训练内存占用低、推理速度快，同时在与低预算模型对比中达到顶尖性能。代码已公开于 https://github.com/jibo27/AHFNet。
原文摘要 · Abstract (English)
State-of-the-art video deblurring methods use deep network architectures to recover sharpened video frames. Blurring especially degrades high-frequency (HF) information, yet this aspect is often overlooked by recent models that focus more on enhancing architectural design. Recovering these fine details is challenging, partly due to the spectral bias of neural networks, which are inclined towards learning low-frequency functions. To address this, we enforce explicit network structures to capture the fine details and edges. We dynamically predict adaptive high-pass kernels from a linear combination of high-pass basis kernels to extract high-frequency features. This strategy is highly efficient, resulting in low-memory footprints for training and fast run times for inference, all while achieving state-of-the-art when compared to low-budget models. The code is available at https://github.com/jibo27/AHFNet.
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。