AI Paper Atlas

Research map / Video / Video segmentation and tracking

Recycle-GAN: Unsupervised Video Retargeting

Aayush Bansal, Shugao Ma, Deva Ramanan, Yaser Sheikh

ECCV 2018 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 345 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 recycle (temporal) loss in place of cycle loss alone (ablation)Cycle-GAN · Viper image-to-labels (all)mean pixel accuracy (%): 35.5 -> 56.0Improved
add recycle (temporal) loss in place of cycle loss alone (ablation)Cycle-GAN · Viper image-to-labels (all)average class accuracy (%): 7.1 -> 11.3Improved
add recycle (temporal) loss in place of cycle loss alone (ablation)Cycle-GAN · Viper image-to-labels (all)IoU (%): 4.2 -> 8.2Improved
combine cycle loss and recycle loss versus recycle loss alone (ablation)Recycle-GAN · Viper image-to-labels (all)IoU (%): 8.2 -> 8.9Improved
combine cycle loss and recycle loss versus recycle loss alone (ablation)Recycle-GAN · Viper image-to-labels (all)mean pixel accuracy (%): 56.0 -> 53.7Hurt
combine cycle loss and recycle loss versus recycle loss alone (night) (ablation)Recycle-GAN · Viper image-to-labels (night)mean pixel accuracy (%): 45.2 -> 33.7Hurt
combine cycle loss and recycle loss versus recycle loss alone (ablation)Recycle-GAN · Viper labels-to-image (all)normalized FCN score: 0.39 -> 0.48Improved
use recycle loss instead of cycle loss (ablation)Cycle-GAN · Viper labels-to-image (all)normalized FCN score: 0.30 -> 0.39Improved
use recycle loss instead of cycle loss (day) (ablation)Cycle-GAN · Viper labels-to-image (day)normalized FCN score: 0.33 -> 0.33No clear effect
use recycle loss instead of cycle loss (rain) (ablation)Cycle-GAN · Viper labels-to-image (rain)normalized FCN score: 0.39 -> 0.37No clear effect
use spatiotemporal recycle loss instead of cycle loss, human realism judgment (ablation)Cycle-GAN · Human study real vs generatedgenerated videos judged real (%): 7.3% -> 28.3%Improved
use spatiotemporal recycle loss instead of cycle loss, pairwise preference (ablation)Cycle-GAN · Human study pairwise naturalnesschosen as more realistic (%): 8% -> 76%Improved

Later papers that compared with this method

1 later accepted paper reports Recycle-GAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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