AI Paper Atlas

Research map / Video / Video segmentation and tracking

Event Stream Super-Resolution via Spatiotemporal Constraint Learning

Siqi Li, Yutong Feng, Yipeng Li, Yu Jiang, Changqing Zou, Yue Gao

ICCV 2021 · Video › Video segmentation and tracking · approach: Space-time video super-resolution · 27 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 spatial loss (spatial distribution learning) (ablation)SNN super-resolution · N-MNISTRMSE_ST: 0.280 -> 0.272Improved
add spatial loss (ablation)SNN super-resolution · CIFAR10-DVSRMSE_ST: 0.183 -> 0.179Improved
add spatial loss (ablation)SNN super-resolution · ASL-DVSRMSE_ST: 0.234 -> 0.229Improved
add temporal loss (temporal distribution learning) (ablation)SNN super-resolution · N-MNISTRMSE_ST: 0.273 -> 0.272Improved
add temporal loss (ablation)SNN super-resolution · CIFAR10-DVSRMSE_ST: 0.180 -> 0.179Improved
add temporal loss (ablation)SNN super-resolution · ASL-DVSRMSE_ST: 0.230 -> 0.229Improved
increase depth from 3 to 4 layers (ablation)SNN super-resolution · N-MNISTRMSE_ST: 0.272 -> 0.278Hurt
increase depth from 3 to 5 layers (ablation)SNN super-resolution · N-MNISTRMSE_ST: 0.272 -> 0.295Hurt
replace Poisson sampling method with spatiotemporal constraint learning SNNLi et al. · Event Camera DatasetRMSE_ST: 0.837 -> 0.325Improved
replace Poisson sampling method with SNN approachLi et al. · N-MNISTRMSE_ST: 0.757 -> 0.272Improved
classify super-resolved HR event streams instead of LR eventsOurs · CIFAR10-DVSaccuracy: 50.8% -> 76.8%Improved
classify our HR streams instead of Li et al. HR streamsOurs · CIFAR10-DVSaccuracy: 59.6% -> 76.8%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