Abstarct:
Video compression technologies have advanced significantly in recent years, achieving high efficiency at conventional bitrates through both traditional and end-to-end AI-based methods. Typical mainstream video streaming services generally operate at bitrates ranging from several hundred kbps to several Mbps, delivering acceptable visual quality. However, a critical challenge arises at ultra low-bitrates (e.g., below 200 kbps), where existing compression methods face substantial degradation in reconstruction quality and compression efficiency. For example, satellite internet services like Starlink typically provide extremely limited bandwidth (often below 200 kbps per user), resulting in poor video quality. Thus, there is a pressing need to improve compression efficiency significantly at ultra low-bitrates. Additionally, at such extreme compression ratios, traditional objective metrics such as PSNR often fail to accurately represent perceptual quality, making perceptual quality assessment especially challenging.
Organizers:
Yunuo Chen, Yibo Shi, Kai Lin.
cyril-chenyn@sjtu.edu.cn,
shiyibo@huawei.com,
linkai30@huawei.com
Abstract:
This challenge invites proposals which optimize VVC encoding processes in order to improve runtime performance of VVC software decoding process while maintaining or minimizing compression efficiency loss which may be incurred in this process.
The challenge is based on publicly available VVC encoder and decoder software: VVdeC [1] and VVenC [2] respectively. We invite proposals which range from optimized encoder configurations to novel video encoding algorithms under the condition that all produced bitstreams are VVCcompliant and can be decoded by the provided VVdeC decoder. Other constraints as described in the challenge will apply.
Organizers:
Justin Ridge, Lukasz Litwic
justin.ridge@nokia.com,
lukasz.litwic@ericsson.com
