AI Paper Atlas

Research map / Video / Video segmentation and tracking

IM-Net for High Resolution Video Frame Interpolation

Tomer Peleg, Pablo Szekely, Doron Sabo, Omry Sendik

CVPR 2019 · Video › Video segmentation and tracking · approach: Video frame interpolation · 92 citations (OpenAlex)

Check 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
use IM-Net instead of TOFlowVimeo 1344 × 768 · Vimeo 1344 × 768PSNR: 30.54 -> 33.11Improved
use IM-Net instead of SepConv - LfVimeo 1344 × 768 · Vimeo 1344 × 768SSIM: 0.9309 -> 0.9436Improved
increase resolution from 448 × 256 to 1344 × 768IM-Net · VimeoPSNR: 33.50 -> 33.11Hurt
increase resolution from 448 × 256 to 1344 × 768SepConv - Lf · VimeoPSNR: 33.45 -> 31.81Hurt
increase resolution from 448 × 256 to 1344 × 768TOFlow · VimeoPSNR: 33.73 -> 30.54Hurt
add warping and symmetry loss terms (ablation)IM-Net · Vimeo SRPSNR: 32.07 -> 33.11Improved
add symmetry loss terms (ablation)IM-Net with warping terms · Vimeo SRPSNR: 32.94 -> 33.11Improved
replace direct motion regression with motion classification (ablation)IM-Net · Global-shift training experimentfull-resolution fidelity lossImproved
use IM-Net instead of SepConv - LfHD inference · HDrun time (msec): 500 -> 30Improved
use IM-Net instead of TOFlowFHD inference · FHDrun time (msec): 880 -> 55Improved

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