Efficient Adaptation of Neural Network Filter for Video Compression
This work addresses video compression efficiency for practical applications, representing an incremental improvement over existing methods.
The paper tackles the problem of adapting neural network filters for video compression by proposing an efficient fine-tuning method that adjusts only convolutional layer biases at the encoder side, achieving up to 9.7% average BD-rate gain compared to the VVC standard.
We present an efficient finetuning methodology for neural-network filters which are applied as a postprocessing artifact-removal step in video coding pipelines. The fine-tuning is performed at encoder side to adapt the neural network to the specific content that is being encoded. In order to maximize the PSNR gain and minimize the bitrate overhead, we propose to finetune only the convolutional layers' biases. The proposed method achieves convergence much faster than conventional finetuning approaches, making it suitable for practical applications. The weight-update can be included into the video bitstream generated by the existing video codecs. We show that our method achieves up to 9.7% average BD-rate gain when compared to the state-of-art Versatile Video Coding (VVC) standard codec on 7 test sequences.