AI Paper Atlas

Research map / Video / Video generation

Learning-based Axial Video Motion Magnification

Kwon Byung-Ki, Oh Hyun-Bin, Kim Jun-Seong, Hyunwoo Ha, Tae-Hyun Oh

ECCV 2024 · Video › Video generation · approach: Trajectory-guided motion control · 4 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
replace 2D convolutions with weight-shared 1D convolutions in the Shape branch and Manipulator (Motion Separation Module) (ablation)Axial motion magnification network · Generic and axial evaluation datasets, subpixel testSSIMImproved
replace 2D convolutions with 1D convolutions (MSM) (ablation)Axial motion magnification network · Generic and axial evaluation datasets, noise testSSIMNo clear effect
add either the angle phi or the magnification map Lambda alone to the DMM-style training data (ablation)Axial motion magnification network · Generic evaluation dataset, subpixel testSSIMNo clear effect
use both phi and Lambda in the synthetic training data (ablation)Axial motion magnification network · Generic evaluation dataset, subpixel testSSIMImproved
add the object-wise magnification map Lambda to the training data (ablation)Axial motion magnification network · Generic evaluation dataset, noise testSSIMImproved
add the angle phi to the training data (ablation)Axial motion magnification network · Generic evaluation dataset, noise testSSIMNo clear effect
use the proposed axial method instead of the modified phase-based baselineAxial motion magnification · Axial evaluation dataset, subpixel and noise testsSSIMImproved
use the proposed method versus DMM and STB-VMM for generic magnificationGeneric motion magnification · Generic evaluation dataset, subpixel testSSIMNo 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