AI Paper Atlas

Research map / Video / Video segmentation and tracking

Fully Automatic Video Colorization With Self-Regularization and Diversity

Chenyang Lei, Qifeng Chen

CVPR 2019 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 116 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 self-regularization instead of removing it (ablation)Ours · DAVISPreference rate: 67.9%Improved
Add diversity loss (ablation)Ours · DAVISPreference rate: 61.5%Improved
Apply BTC temporal consistency refinementZhang et al. · DAVIS and VidevoLPIPS and PSNR: DAVIS LPIPS 0.218 -> 0.243; PSNR 29.25 -> 29.07; Videvo LPIPS 0.201 -> 0.249; PSNR 29.52 -> 29.04Hurt
Apply BTC temporal consistency refinementIizuka et al. · DAVIS and VidevoLPIPS and PSNR: DAVIS LPIPS 0.189 -> 0.218; PSNR 29.91 -> 29.25; Videvo LPIPS 0.190 -> 0.241; PSNR 30.23 -> 28.90Hurt
Use the proposed video colorization method rather than Zhang et al. + BTCFully automatic video colorization · DAVIS and VidevoPerceptual preference rate: 80.0%; 88.8%Improved
Use the proposed video colorization method rather than Iizuka et al. + BTCFully automatic video colorization · DAVIS and VidevoPerceptual preference rate: 72.8%; 63.3%Improved

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