Implicit Neural Video Compression
This work addresses video compression for applications needing efficient encoding, but it appears incremental as it builds on implicit neural representations without claiming major performance breakthroughs.
The authors tackled video compression by representing each frame as a neural network mapping coordinates to pixels, using implicit neural representations with motion compensation and quantization, achieving feasibility in compressing full-resolution video sequences.
We propose a method to compress full-resolution video sequences with implicit neural representations. Each frame is represented as a neural network that maps coordinate positions to pixel values. We use a separate implicit network to modulate the coordinate inputs, which enables efficient motion compensation between frames. Together with a small residual network, this allows us to efficiently compress P-frames relative to the previous frame. We further lower the bitrate by storing the network weights with learned integer quantization. Our method, which we call implicit pixel flow (IPF), offers several simplifications over established neural video codecs: it does not require the receiver to have access to a pretrained neural network, does not use expensive interpolation-based warping operations, and does not require a separate training dataset. We demonstrate the feasibility of neural implicit compression on image and video data.