用双摄图像提升手机画质，通过域调制和多尺度匹配实现精准细节恢复。
DM$^3$Net: Dual-Camera Super-Resolution via Domain Modulation and Multi-scale Matching
- 通过域调制学习双图域间特征表示，缩小分辨率差异。
- 多尺度匹配模块提升高频细节迁移准确率，鲁棒性更强。
- 引入关键剪枝技术，大幅降低内存与推理时间，适合移动端部署。
双摄像头超分辨率在智能手机摄影中具有重要意义，主要通过参考长焦图像来超分辨广角图像。本文提出DM$^3$Net，一种基于域调制与多尺度匹配的新型双摄像头超分辨率网络。为弥合高分辨率域与退化域之间的域差距，我们从图像对中学习两个压缩的全局表示。为可靠传递参考图像中的高频结构细节，设计了多尺度匹配模块，在多个感受野下进行像素级特征匹配与检索，提升匹配精度与鲁棒性。此外，引入关键剪枝（Key Pruning）技术，在几乎不损失性能的前提下显著降低内存占用与推理时间。在三个真实世界数据集上的实验结果表明，所提方法优于现有最先进方法。
原文摘要 · Abstract (English)
Dual-camera super-resolution is highly practical for smartphone photography that primarily super-resolve the wide-angle images using the telephoto image as a reference. In this paper, we propose DM$^3$Net, a novel dual-camera super-resolution network based on Domain Modulation and Multi-scale Matching. To bridge the domain gap between the high-resolution domain and the degraded domain, we learn two compressed global representations from image pairs corresponding to the two domains. To enable reliable transfer of high-frequency structural details from the reference image, we design a multi-scale matching module that conducts patch-level feature matching and retrieval across multiple receptive fields to improve matching accuracy and robustness. Moreover, we also introduce Key Pruning to achieve a significant reduction in memory usage and inference time with little model performance sacrificed. Experimental results on three real-world datasets demonstrate that our DM$^3$Net outperforms the state-of-the-art approaches.
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。