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.
Original languageEnglish
Number of pages8
Publication statusPublished - 13 Dec 2021
EventNeurIPS 2021 Pre-Registration Workshop: An Alternative Publication Model for Machine Learning research - Online
Duration: 13 Dec 202113 Dec 2021


WorkshopNeurIPS 2021 Pre-Registration Workshop
Abbreviated titlePreReg@NeurIPS'21
Internet address


  • image encoding
  • machine learning
  • neural networks
  • CbMLP
  • video compression


Dive into the research topics of 'Neural weight step video compression'. Together they form a unique fingerprint.

Cite this