AI Paper Atlas

Research map / Video / Video segmentation and tracking

3R-INN: How to be climate friendly while consuming/delivering videos?

ZOUBIDA AMEUR, Claire-Helene Demarty, Olivier LE MEUR, Daniel Menard

ECCV 2024 · Video › Video segmentation and tracking · approach: Learned video compression · 6 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 conditional latent encoding block (condition latent mean/variance on LR image) (ablation)3R-INN · DIV2K val grainy HRJSD-NSS: 0.0096 -> 0.0090Improved
add conditional latent encoding block (ablation)3R-INN · DIV2K val clean LRPSNR: 38.62 -> 38.71No clear effect
increase lambda1 weight of forward fidelity loss to 40 (ablation)3R-INN · DIV2K val clean LRPSNR: 38.71 -> 39.30Improved
increase lambda1 to 40 (ablation)3R-INN · DIV2K val clean HRPSNR: 35.53 -> 35.41Hurt
increase film grain latent dimension dim(z_G) beyond 1 (ablation)3R-INN · DIV2K valclean LR/HR PSNR: 39.45 -> 39.30 LR PSNR for dim 1 vs 2Hurt
optimize RGBW OLED power model instead of luminance model P_Y3R-INN energy-aware task · DIV2K, R=20%PSNR-Y: 27.32 -> 38.02Improved
use single invertible network vs IRN for rescaling plus grain removal3R-INN · DIV2K clean LRPSNR: 39.06 -> 39.63Improved
3R-INN vs IRN on clean HR reconstruction3R-INN · DIV2K clean HRPSNR: 36.53 -> 35.43Hurt
encode low-res grain-free energy-aware video instead of HR grainyvideo chain (RaceHorses, QP22, R=20%) · RaceHorsesenergy savings: 78% encoding, 3% delivery, ca. 77% decodingImproved
energy-aware reduction rate R on OLED display3R-INN · RaceHorses on LG-42C2 OLEDdisplay power reduction: 6.8%, 21.5%, 33.3%, 44.2% for R=5/20/40/60%Improved

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