PocketDVDNet：为真实相机噪声实现实时视频去噪
PocketDVDNet: Realtime Video Denoising for Real Camera Noise
AI总结：
PocketDVDNet通过模型压缩框架结合稀疏引导剪枝、物理噪声模型和知识蒸馏，实现高效实时视频去噪，减少模型大小74%并提升去噪质量。
摘要：
在现实中的多成分传感器噪声下，实时视频去噪仍然对应用如自动对焦、自动驾驶和监控等具有挑战性。我们提出了PocketDVDNet，一种轻量级视频去噪器，采用我们模型压缩框架开发，结合了稀疏引导的结构剪枝、物理指导的噪声模型和知识蒸馏，以实现高质量的恢复，同时减少资源需求。从参考模型开始，我们诱导稀疏性，应用定向通道剪枝，并在现实的多成分噪声上重新训练教师模型。学生网络学习隐式噪声处理，消除了对显式噪声图输入的需求。PocketDVDNet将原始模型大小减少了74%，同时提高了去噪质量，并实时处理5帧块。这些结果表明，结合领域适应的蒸馏，可以平衡性能和效率，以实现实用的实时视频去噪。
英文摘要：
Live video denoising under realistic, multi-component sensor noise remains challenging for applications such as autofocus, autonomous driving, and surveillance. We propose PocketDVDNet, a lightweight video denoiser developed using our model compression framework that combines sparsity-guided structured pruning, a physics-informed noise model, and knowledge distillation to achieve high-quality restoration with reduced resource demands. Starting from a reference model, we induce sparsity, apply targeted channel pruning, and retrain a teacher on realistic multi-component noise. The student network learns implicit noise handling, eliminating the need for explicit noise-map inputs. PocketDVDNet reduces the original model size by 74% while improving denoising quality and processing 5-frame patches in real-time. These results demonstrate that aggressive compression, combined with domain-adapted distillation, can reconcile performance and efficiency for practical, real-time video denoising.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
