AI Paper Atlas

Research map / Video / Video segmentation and tracking

Scene Matters: Model-based Deep Video Compression

Lv Tang, Xinfeng Zhang, Gai Zhang, Xiaoqi Ma

ICCV 2023 · 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
add context-related spatial positional embedding (CRSPE) to baseline video INR (ablation)video INR baseline · Surveillance-1BDBR vs H.266 (%): 13.82 -> 3.15Improved
add frequency domain supervision (FDS) (ablation)MVC with CRSPE · Surveillance-1BDBR vs H.266 (%): 3.15 -> -3.53Improved
add scene flow constrain mechanism (SFCM) (ablation)MVC with CRSPE+FDS · Surveillance-1BDBR vs H.266 (%): -3.53 -> -18.65Improved
add temporal contrastive loss (TCL) (ablation)MVC with CRSPE+FDS+SFCM · Surveillance-1BDBR vs H.266 (%): -18.65 -> -22.97Improved
add flow regularization to SFCM (ablation)MVC · ConferenceBDBR vs H.266 (%): 4.33 -> -4.21Improved
add entropy loss L_ent on regularization map (ablation)MVC SFCM · Surveillance-1BDBR vs H.266 (%): -16.69 -> -18.65Improved
add prior Gaussian distribution weighting to TCL (ablation)MVC TCL · Surveillance-1BDBR vs H.266 (%): -18.12 -> -22.97Improved
reduce TCL frame window L from 80 to 40 (ablation)MVC TCL · Surveillance-1BDBR vs H.266 (%): -22.97 -> -19.85Hurt
increase TCL frame window L from 80 to 120 (ablation)MVC TCL · Surveillance-1BDBR vs H.266 (%): -22.97 -> -21.97No clear effect
transmit CRSPE embeddingMVC 720p videos · 720p videosbitrate and PSNR: extra 10% Bpp for about 0.9dB PSNRMixed
use multi-GPU parallel decodingMVC · 600 1080p frames decodingdecoding speed: about 132 s on one GPU; real-time 35 FPS with more GPUsImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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