AI Paper Atlas

Research map / Video / Video segmentation and tracking

Artistic Style Transfer for Videos and Spherical Images

Manuel Ruder, Alexey Dosovitskiy, Thomas Brox

IJCV 2018 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 144 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
initialize with motion-compensated previous frame instead of unwarped previous frame (ablation)optimization-based video style transfer · MPI Sintel alley_2temporal MSE: 0.010 -> 0.0016Improved
add explicit temporal penalty (ablation)optimization-based video style transfer · MPI Sintel alley_2temporal MSE: 0.0016 -> 0.00061Improved
use DeepFlow instead of EpicFlow (ablation)optimization-based video style transfer · MPI Sintel alley_2temporal MSE: 0.00073 -> 0.00061Improved
add dilated convolutions instead of strided downsampling (ablation)network-based style transfer · MPI Sinteltemporal loss vs baseline: 100% -> 67%Improved
train with two frames and a prior image (ablation)network-based style transfer · MPI Sinteltemporal loss vs baseline: 100% -> 41% temporal; style 100% -> 167%Mixed
add multi-frame training over two-frame training (ablation)network-based style transfer · MPI Sintelstyle loss vs baseline: 167% -> 85%Improved
add mixed training (zero-prior samples) to multi-frame training (ablation)network-based style transfer · MPI Sintelstyle loss vs baseline: 85% -> 77%Improved
replace independent per-frame network with prior-image networknetwork-based style transfer · MPI Sintel alley_2temporal MSE: 0.0062 -> 0.0016Improved
add prior image from neighboring cube face bordernetwork-based style transfer · spherical imagescut-edge gradient E_grad_cut: 2.48 -> 1.40Improved
fine-tune video net on spherical-specific dataset (ablation)network-based style transfer · spherical imagesE_grad: 1.41 -> 1.21Improved
fill missing prior regions with random noise instead of zeros (ablation)network-based style transfer · spherical imagesE_grad: 1.21 -> 1.18Improved
add multi-pass algorithm (ablation)optimization-based video style transfer · Miss Marple scene (qualitative)image brightness and contrast over timeImproved

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