AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video compression dataset and benchmark of learning-based video-quality metrics

Anastasia Antsiferova, Sergey Lavrushkin, Maksim Smirnov, Aleksandr Gushchin, Dmitriy S. Vatolin, Dmitriy Kulikov

NeurIPS 2022 · Video › Video segmentation and tracking · approach: Learned video compression · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
include chroma (YUV) components in VMAF instead of luma only (ablation)VMAF · full datasetSROCC: 0.942 -> 0.943Improved
use VMAF NEG (no enhancement gain) instead of original VMAF (ablation)VMAF · full datasetSROCC: 0.943 -> 0.917Hurt
use no-reference MDTVSFA instead of best full-reference VMAFVMAF · full datasetSROCC: 0.943 vs 0.929No clear effect
use mixed-dataset training MDTVSFA instead of VSFAVSFA · full datasetSROCC: 0.905 -> 0.929Improved
evaluate at high bitrate (>6,000 kbps) vs all videosY-VMAF (v061) · video quality metricsSROCC: 0.942 -> 0.453Hurt
evaluate on VVC-encoded videos vs best on allMDTVSFA · video quality metricsSROCC: 0.929 -> 0.882Hurt
use learned perceptual metrics (LPIPS, DISTS) vs classical SSIM/PSNRLPIPS · full datasetSROCC: 0.906 (YUV-SSIM) -> 0.749 (LPIPS)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy