Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set
This improves video compression efficiency for applications like streaming or storage, offering significant gains over existing methods.
The paper tackles video compression by finetuning a pretrained neural codec on each video sequence, transmitting both the adapted parameters and latent code, achieving 17-27% BD-rate savings on standard datasets and enabling competitive performance with 70% smaller networks.
We introduce a video compression algorithm based on instance-adaptive learning. On each video sequence to be transmitted, we finetune a pretrained compression model. The optimal parameters are transmitted to the receiver along with the latent code. By entropy-coding the parameter updates under a suitable mixture model prior, we ensure that the network parameters can be encoded efficiently. This instance-adaptive compression algorithm is agnostic about the choice of base model and has the potential to improve any neural video codec. On UVG, HEVC, and Xiph datasets, our codec improves the performance of a scale-space flow model by between 21% and 27% BD-rate savings, and that of a state-of-the-art B-frame model by 17 to 20% BD-rate savings. We also demonstrate that instance-adaptive finetuning improves the robustness to domain shift. Finally, our approach reduces the capacity requirements of compression models. We show that it enables a competitive performance even after reducing the network size by 70%.