DeepAI AI Chat
Log In Sign Up

Differentiable bit-rate estimation for neural-based video codec enhancement

by   Amir Said, et al.

Neural networks (NN) can improve standard video compression by pre- and post-processing the encoded video. For optimal NN training, the standard codec needs to be replaced with a codec proxy that can provide derivatives of estimated bit-rate and distortion, which are used for gradient back-propagation. Since entropy coding of standard codecs is designed to take into account non-linear dependencies between transform coefficients, bit-rates cannot be well approximated with simple per-coefficient estimators. This paper presents a new approach for bit-rate estimation that is similar to the type employed in training end-to-end neural codecs, and able to efficiently take into account those statistical dependencies. It is defined from a mathematical model that provides closed-form formulas for the estimates and their gradients, reducing the computational complexity. Experimental results demonstrate the method's accuracy in estimating HEVC/H.265 codec bit-rates.


page 1

page 2

page 3

page 4


Deep Vocoder: Low Bit Rate Compression of Speech with Deep Autoencoder

Inspired by the success of deep neural networks (DNNs) in speech process...

Deep Vocoder: Low Bit Rate Speech Compression of Speech with Deep Autoencoder

Inspired by the success of deep neural networks (DNNs) in speech process...

Sandwiched Video Compression: Efficiently Extending the Reach of Standard Codecs with Neural Wrappers

We propose sandwiched video compression – a video compression system tha...

Variable-Bitrate Neural Compression via Bayesian Arithmetic Coding

Deep Bayesian latent variable models have enabled new approaches to both...

Variable Rate Video Compression using a Hybrid Recurrent Convolutional Learning Framework

In recent years, neural network-based image compression techniques have ...

FAIVConf: Face enhancement for AI-based Video Conference with Low Bit-rate

Recently, high-quality video conferencing with fewer transmission bits h...

Pseudocylindrical Convolutions for Learned Omnidirectional Image Compression

Although equirectangular projection (ERP) is a convenient form to store ...