Coding Standards as Anchors for the CVPR CLIC video track

TL;DR

This paper evaluates the performance of learned video compression techniques against standardized coders like VVC in the context of the CVPR CLIC video track, emphasizing reproducibility and progress measurement.

Contribution

It introduces a reproducible method for generating coded videos that meet challenge requirements, enabling fair comparison and progress tracking of learning-based methods.

Findings

Quantifies progress of learning techniques over years

Provides a reproducible pipeline for video coding evaluation

Assesses performance of VVC in a standardized setting

Abstract

In 2021, a new track has been initiated in the Challenge for Learned Image Compression~: the video track. This category proposes to explore technologies for the compression of short video clips at 1 Mbit/s. This paper proposes to generate coded videos using the latest standardized video coders, especially Versatile Video Coding (VVC). The objective is not only to measure the progress made by learning techniques compared to the state of the art video coders, but also to quantify their progress from years to years. With this in mind, this paper documents how to generate the video sequences fulfilling the requirements of this challenge, in a reproducible way, targeting the maximum performance for VVC.