Papers › Reducing the Sim-to-Real Gap for Event Cameras

Reducing the Sim-to-Real Gap for Event Cameras

20 Mar 2020ECCV 2020 8arXiv:2003.09078archive 2025-07-28

Timo Stoffregen, Cedric Scheerlinck, Davide Scaramuzza, Tom Drummond, Nick Barnes, Lindsay Kleeman, Robert Mahony

Event cameras are paradigm-shifting novel sensors that report asynchronous, per-pixel brightness changes called 'events' with unparalleled low latency. This makes them ideal for high speed, high dynamic range scenes where conventional cameras would fail. Recent work has demonstrated impressive results using Convolutional Neural Networks (CNNs) for video reconstruction and optic flow with events. We present strategies for improving training data for event based CNNs that result in 20-40% boost in performance of existing state-of-the-art (SOTA) video reconstruction networks retrained with our method, and up to 15% for optic flow networks. A challenge in evaluating event based video reconstruction is lack of quality ground truth images in existing datasets. To address this, we present a new High Quality Frames (HQF) dataset, containing events and ground truth frames from a DAVIS240C that are well-exposed and minimally motion-blurred. We evaluate our method on HQF + several existing major event camera datasets.

PaperPDFConference PDFCode

Code

TimoStoff/event_cnn_minimal mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Event-Based Video ReconstructionVideo Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Reconstruction Event-Camera Dataset E2VID+ LPIPS 0.236 #3 of 4 Archive leaderboard report
Video Reconstruction Event-Camera Dataset E2VID+ Mean Squared Error 0.070 #3 of 4 Archive leaderboard report
Video Reconstruction MVSEC E2VID+ LPIPS 0.514 #3 of 4 Archive leaderboard report
Video Reconstruction MVSEC E2VID+ Mean Squared Error 0.132 #3 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections