AI Paper Atlas

Research map / Video / Video segmentation and tracking

Extending Neural P-Frame Codecs for B-Frame Coding

Reza Pourreza, Taco Cohen

ICCV 2021 · Video › Video segmentation and tracking · approach: Learned video compression · 47 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 frame interpolation of two references so a P-frame codec codes B-frames (B-EPIC vs SSF)SSF P-frame codec · UVGPSNR BD-rate gain vs H.264 (%): -25.71 -> -47.89Improved
add frame interpolation of two references so a P-frame codec codes B-frames (B-EPIC vs SSF)SSF P-frame codec · UVGMS-SSIM BD-rate gain vs H.264 (%): -41.05 -> -50.79Improved
add frame interpolation of two references so a P-frame codec codes B-frames (B-EPIC vs SSF)SSF P-frame codec · MCL-JCVPSNR BD-rate gain vs H.264 (%): -15.90 -> -31.91Improved
add frame interpolation of two references so a P-frame codec codes B-frames (B-EPIC vs SSF)SSF P-frame codec · HEVC-CPSNR BD-rate gain vs H.264 (%): 47.69 -> 11.22Improved
add frame interpolation of two references so a P-frame codec codes B-frames (B-EPIC vs SSF)SSF P-frame codec · HEVC-DMS-SSIM BD-rate gain vs H.264 (%): -20.79 -> -43.98Improved
B-EPIC (MSE) vs H.265 in PSNR on small-resolution HEVC-D (padding to multiple of 64)B-EPIC (MSE) · HEVC-DPSNR BD-rate gain vs H.264 (%): -16.25 -> 29.05Hurt
use FFMPEG default parameters for H.264/H.265 anchors instead of GoP=12 settingsB-EPIC (MSE) · UVGPSNR BD-rate gain vs H.264 (%): -47.89 -> -26.93Hurt
train on longer or sparser sequences (7 consecutive frames, or 4 frames two apart) instead of 4 consecutive frames (ablation)B-EPIC · UVGrate-distortionNo clear effect
increase training GoP length (ablation)B-EPIC · Vimeo-90k trainingrate-distortionNo clear effect

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