AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Learning to See in the Dark with Events

Song Zhang, Yu Zhang, Zhe Jiang, Dongqing Zou, Jimmy Ren, Bin Zhou

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 69 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 noise channel (ablation)Event-to-image domain adaptation · DVS-Dark simulatedPSNR: 20.69 -> 21.24Improved
add detail enhancing branch (ablation)Event-to-image domain adaptation · DVS-Dark simulatedPSNR: 21.24 -> 24.91Improved
add ranking regularization (ablation)Event-to-image domain adaptation · DVS-Dark simulatedPSNR: 24.91 -> 26.03Improved
add ranking regularization (ablation)Event-to-image domain adaptation · DVS-Dark simulatedSSIM: 0.75 -> 0.77Improved
add detail recovery on top of shared-space reconstruction (SDA)SDA · DVS-Dark simulatedPSNR: 24.93 -> 26.03Improved
add domain adaptation to Pix2Pix baselinePix2Pix · DVS-Dark simulatedPSNR: 22.65 -> 26.03Improved
fine-tune E2V on day-light images of DVS-DarkE2V · DVS-Dark simulatedPSNR: 12.16 -> 17.15Improved
use ranking loss weight 5.0 instead of 1.0 (ablation)Ranking regularization · DVS-Darkvisual qualityHurt
use ranking loss weight 1.0 (ablation)Ranking regularization · DVS-Darkvisual qualityImproved
use ours instead of Pix2Pix on real low-light eventsPix2Pix · DVS-Dark real low lightFID: 109.08 -> 104.21Improved
use ours instead of E2V on real low-light eventsE2V · DVS-Dark real low lightFID: 210.42 -> 104.21Improved
train with ranking loss margin 0.5 (ablation)Ranking regularization · DVS-DarkPSNRNo clear effect

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