AI Paper Atlas

Research map / Video / Video segmentation and tracking

NVC-1B: Scaling up Neural Video Coding Models

CP Tang, Xihua Sheng, Li Li, Dong Liu, Feng Wu

TPAMI 2026 · Video › Video segmentation and tracking · approach: Learned video compression · 9 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
scale motion encoder-decoder from 52M to 96M (ablation)DCVC-SDD · HEVC Class CBD-rate gain (%): 15.4% -> 1.5%Hurt
scale motion entropy model (M1 to M4) (ablation)DCVC-SDD · HEVC Class CBD-rate gain (%): 15.4% -> 16.0%Improved
scale contextual encoder-decoder from 50M to 90M (ablation)DCVC-SDD · HEVC Class CBD-rate gain (%): 10.6% -> 14.8%Improved
scale contextual entropy model from 90M to 212M (ablation)DCVC-SDD · HEVC Class CBD-rate gain (%): additional 0.8%Improved
scale temporal context mining from 26M to 75M (ablation)DCVC-SDD · HEVC Class DBD-rate gain (%): 5.1% -> 12.0%Improved
scale temporal context mining on top of M12 (M18) (ablation)DCVC-SDD · HEVC Class DBD-rate gain (%): 14.2% -> 21.2%Improved
use mixed CNN-Transformer instead of CNN at similar size (ablation)DCVC-SDD scaled model · HEVC Class CBD-rate gain (%): 15.6% -> 9.4%Hurt
insert Swin layers into temporal context mining (ablation)M20 · HEVC Class CBD-rate gain (%): 9.4% -> 2.9%Hurt
replace convolutions with Transformer-only entropy model and temporal context (ablation)DCVC-SDD scaled model · RGB-PSNRBD-rate gain (%): PSNR loss of more than 4dBHurt
scale up to NVC-1B (1.36B parameters)DCVC-SDD · RGB average BD-rate vs VTMBD-rate gain (%): -12.7 -> -25.1Improved
scale up to NVC-1BDCVC-SDD · YUV average BD-rate vs VTMBD-rate gain (%): -8.4 -> -20.5Improved
scale up to NVC-1BDCVC-SDD · 1080P encoding timeBD-rate gain (%): 0.89 s -> 4.44 sHurt

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