AI Paper Atlas

Research map / Video / Video segmentation and tracking

Motion Information Propagation for Neural Video Compression

Linfeng Qi, Jiahao Li, Bin Li, Houqiang Li, Yan Lu

CVPR 2023 · Video › Video segmentation and tracking · approach: Learned video compression · 33 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
replace DCVC-HEM with DCVC-MIPneural video compression · Average across UVG, MCL-JCV, HEVC B/C/D/E and HEVC RGBBD-Rate (%) PSNR: -4.7 -> -16.6Improved
replace DCVC-HEM with DCVC-MIPneural video compression · Average across UVG, MCL-JCV, HEVC B/C/D/E and HEVC RGBBD-Rate (%) MS-SSIM: -46.4 -> -50.8Improved
add offset diversity (ablation)DCVC-MIP context generation · average benchmark performanceBD-Rate (%): 0.0 -> -2.6Improved
add motion guidance (ablation)DCVC-MIP context generation · average benchmark performanceBD-Rate (%): -2.6 -> -5.9Improved
add motion condition (ablation)DCVC-MIP motion coding · average benchmark performanceBD-Rate (%): -5.9 -> -9.4Improved
add transformer-based context refinement (ablation)DCVC-MIP context generation · average benchmark performanceBD-Rate (%): -9.4 -> -12.9Improved
use motion feature Gt rather than decoded motion flow as guidance (ablation)DCVC-MIP · average benchmark performanceBD-Rate (%): -2.4 -> -3.2Improved
use propagated feature Ht−1 as motion condition (ablation)DCVC-MIP motion coding · average benchmark performanceBD-Rate (%): -3.2 -> -6.9Improved
use residual offsets Rt−1 rather than feature Ht−1 as motion condition (ablation)DCVC-MIP motion coding · average benchmark performanceBD-Rate (%): -6.9 -> -4.6Hurt
apply transformer-based context refinement at 1/4 scale (ablation)DCVC-MIP context generation · average benchmark performanceBD-Rate (%): 0.0 -> -3.2Improved
apply RSTB to the entropy model instead of TCR at 1/4 scale (ablation)DCVC-MIP entropy model · average benchmark performanceBD-Rate (%): -3.2 -> -1.4Hurt

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