DeepAI AI Chat
Log In Sign Up

Implicit Neural Video Compression

by   Yunfan Zhang, et al.

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.


FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos

Neural fields, also known as coordinate-based or implicit neural represe...

Optical Flow Regularization of Implicit Neural Representations for Video Frame Interpolation

Recent works have shown the ability of Implicit Neural Representations (...

Neural Weight Step Video Compression

A variety of compression methods based on encoding images as weights of ...

Video Frame Synthesis using Deep Voxel Flow

We address the problem of synthesizing new video frames in an existing v...

L_0onie: Compressing COINs with L_0-constraints

Advances in Implicit Neural Representations (INR) have motivated researc...

End-to-end Optimized Video Compression with MV-Residual Prediction

We present an end-to-end trainable framework for P-frame compression in ...

PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence

We present a novel method to learn Personalized Implicit Neural Avatars ...