AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning to Robustly Reconstruct Dynamic Scenes from Low-light Spike Streams

Liwen Hu, Ziluo Ding, Mianzhi Liu, Lei Ma, Tiejun Huang

ECCV 2024 · 3D vision › Depth and stereo · approach: Spike and event camera reconstruction · 3 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 LR-Rep to the basic baseline (ablation)bidirectional recurrent reconstruction network · LLRPSNR: 42.743 -> 44.739Improved
add adjacent forward/backward deep temporal features (ADF) (ablation)bidirectional recurrent reconstruction network · LLRPSNR: 42.743 -> 44.151Improved
add alignment information (PCD) in fusion module (ablation)full method · LLRPSNR: 44.956 -> 45.075Improved
use GISI instead of LISI in LR-Rep (ablation)LR-Rep · LLRPSNR: 44.997 -> 45.075Improved
use LR-Rep instead of other spike representations (TFP, TFI, AST, AMIM, SALI, WGSE-1d) (ablation)reconstruction framework · LLRPSNR: 43.314 (SALI, best other) -> 45.075Improved
increase training data from 20% to 100% of RLLR (ablation)full method · LLRPSNR: 35.001 -> 45.075Improved
increase number of continuous spike streams maintained recurrently from 1 to 21 (ablation)full method · LLRPSNR: 43.005 -> 45.075Improved
proposed method versus WGSE state of the artspike reconstruction · LLRPSNR: 42.959 -> 45.075Improved

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