AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Video Frame Interpolation Using Cyclic Frame Generation

Yu-Lun Liu, Yi-Tung Liao, Yen-Yu Lin, Yung-Yu Chuang

AAAI 2019 · Video › Video segmentation and tracking · approach: Video frame interpolation · 165 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 cycle consistency loss (ablation)DVF · UCF101 testPSNR: 35.89 -> 36.71Improved
add motion linearity loss (ablation)DVF + cycle loss · UCF101 testPSNR: +0.14dBImproved
add edge-guided training (HED edge maps as input) (ablation)DVF + cycle loss · UCF101 testPSNR: +0.15dBImproved
add cycle and motion linearity losses under reduced training data (1/1000)DVF · UCF101 testPSNR: 34.42 -> 36.10Improved
full method vs SepConvDVF · UCF101 testPSNR: 36.49 -> 36.96Improved
full method vs CtxSynDVF · Middleburyaverage interpolation error: 5.28 -> 4.20Improved
extend cycle to three-step loop (ablation)CyclicGen · UCF101PSNRNo clear effect
skip first-stage pretraining (train end-to-end from scratch) (ablation)CyclicGen · UCF101PSNRHurt

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