AI Paper Atlas

Research map / Video / Video segmentation and tracking

Revisit Event Generation Model: Self-Supervised Learning of Event-to-Video Reconstruction with Implicit Neural Representations

Zipeng Wang, yunfan lu, Lin Wang

ECCV 2024 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 7 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 regularization (ablation)EvINR · IJRRMSE: 0.063 -> 0.044Improved
add coarse-to-fine training (ablation)EvINR · IJRRtraining time (s): 17.29 -> 7.94Improved
add coarse-to-fine training (ablation)EvINR · IJRRMSE: 0.063 -> 0.061No clear effect
frame-based instead of coordinate-based optimizationEvINR · event sequencesconvergence time: minutes -> secondsImproved
ensemble 10 networks of 5 s each instead of one network (ablation)EvINR · IJRR CalibrationMSE: 0.084 -> 0.0625Improved
increase ensemble partitions to 50 (1 s each) (ablation)EvINR · IJRR CalibrationMSE: 0.0625 -> 0.0875Hurt
self-supervised EvINR versus supervised methods on a new sensorEvINR · AEDSSIM: 0.345 -> 0.458Improved
EvINR versus best supervised method on lower-density eventsEvINR · HQFMSE: 0.032 vs 0.048Hurt
EvINR versus prior SSL methodEvINR · IJRRMSE: 0.097 -> 0.047Improved

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