Neural Weight Step Video Compression
This addresses video compression efficiency, potentially benefiting multimedia applications, but appears incremental as it builds on existing neural image compression methods.
The paper explores the feasibility of compressing video by encoding frames as neural network weights, proposing a novel neural weight stepping technique where subsequent frames are encoded as low-entropy parameter updates. It tests this approach on high-resolution video datasets against existing compression methods.
A variety of compression methods based on encoding images as weights of a neural network have been recently proposed. Yet, the potential of similar approaches for video compression remains unexplored. In this work, we suggest a set of experiments for testing the feasibility of compressing video using two architectural paradigms, coordinate-based MLP (CbMLP) and convolutional network. Furthermore, we propose a novel technique of neural weight stepping, where subsequent frames of a video are encoded as low-entropy parameter updates. To assess the feasibility of the considered approaches, we will test the video compression performance on several high-resolution video datasets and compare against existing conventional and neural compression techniques.