LiteDVDNet: Optimizing FastDVDNet for High-Speed Video Denoising

The growing demand for high-quality video processing in real-time applications demands efficient denoising techniques that can operate swiftly while maintaining visual fidelity. Conventional approaches often struggle to balance these competing requirements, especially when dealing with high-resolution video streams or resource-constrained environments. This study aims to develop methods for accelerating video data denoising using deep convolutional neural networks while maintaining acceptable output quality. We selected the popular FastDVDNet denoising network, which operates on a sliding window principle, as our baseline for comparison and a starting point for our research. This paper proposes several modifications of FastDVDNet that significantly enhance computational efficiency. We introduce four key optimizations: caching intermediate denoising results, reducing intermediate channels in input block, simplifying convolutional blocks, and halving the number of channels. We evaluated these modifications on the Set8 dataset and compared the results with the original model at various noise levels. Finally, we introduce LiteDVDNet, a fine-tuned version of FastDVDNet model that achieves the optimal balance between processing speed, and denoising performance. We developed two model variants: LiteDVDNet-32, which is 3× faster than the original model with only 0.18 dB average PSNR reduction, and the more lightweight LiteDVDNet-16, which delivers a 5× speed improvement at the cost of 0.61 dB average PSNR reduction.