AI Paper Atlas

Research map / Video / Video segmentation and tracking

Online-Trained Upsampler for Deep Low Complexity Video Compression

Jan P. Klopp, Keng-Chi Liu, Shao-Yi Chien, Liang-Gee Chen

ICCV 2021 · 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
add reptile initialisation pre-training (ablation)Online-trained upsampler · eight high-resolution datasetsBD-rate and BD-PSNRImproved
add codec internal features (motion vectors, relative block positions) (ablation)Online-trained upsampler · eight high-resolution datasetsBD-rate and BD-PSNRImproved
add trigonometric position encoding (ablation)Online-trained upsampler · eight high-resolution datasetsBD-rate and BD-PSNRImproved
use only low-frequency position encodings instead of high frequencies (ablation)Online-trained upsampler · position encodingpredictive capabilityImproved
use position-aware upsampler instead of online-trained denoiser [16]Online-trained upsampler · JVET A (32 frames)BD-rate: -5.7% -> -18.4%Improved
use position-aware upsampler instead of online-trained denoiser [16]Online-trained upsampler · Netflix (32 frames)BD-rate: -5.0% -> -27.5%Improved
use position-aware upsampler instead of online-trained denoiser [16]Online-trained upsampler · CTC A (32 frames)BD-rate: -9.1% -> -13.6%Improved
increase frame group size from 32 to 128 (ablation)Online-trained upsampler · NetflixBD-rate: -27.5% -> -20.6%Hurt
increase frame group size from 32 to 128 (ablation)Online-trained upsampler · JVET ABD-rate: -18.4% -> -19.6%Improved
increase frame group size from 32 to 128 (ablation)Online-trained upsampler · JVET A UHD, QP 22encoding time per frame: 2.40s -> 1.11sImproved
train on only the first N frames of a 32-frame group, N below half (ablation)Online-trained upsampler · offline generalisationBD-rateHurt
raise signalling frequency from 8 to 32 frames in zero-latency mode (ablation)Online-trained upsampler · Netflix (zero-latency)BD-rate: -17.2% -> -8.6%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