PocketDVDNet: Realtime Video Denoising for Real Camera Noise
This addresses the problem of efficient video denoising for applications like autofocus and surveillance, representing an incremental improvement through model compression.
The paper tackled real-time video denoising under realistic sensor noise by proposing PocketDVDNet, a lightweight model that reduces the original model size by 74% while improving denoising quality and processing 5-frame patches in real-time.
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.