AI Paper Atlas

Research map / 3D vision / Depth and stereo

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Chankyu Lee, Adarsh Kumar Kosta, Alex Zihao Zhu, Kenneth Chaney, Kostas Daniilidis, Kaushik Roy

ECCV 2020 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 214 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
convert the first residual block from ANN to SNN (ablation)Spike-FlowNet · MVSEC indoor2 (dt=1)AEE: 1.28 -> 1.55Hurt
convert both residual blocks from ANN to SNN (ablation)Spike-FlowNet · MVSEC indoor2 (dt=1)AEE: 1.28 -> 1.56Hurt
convert the first residual block from ANN to SNN (ablation)Spike-FlowNet · MVSEC indoor2 (dt=4)AEE: 3.83 -> 4.46Hurt
convert both residual blocks from ANN to SNN (ablation)Spike-FlowNet · MVSEC indoor2 (dt=4)AEE: 3.83 -> 4.61Hurt
increase number of event groups N from 2 to 4 (ablation)Spike-FlowNet · MVSEC indoor2 (dt=1)AEE: 1.28 -> 1.76Hurt
increase number of event groups N from 2 to 3 (ablation)Spike-FlowNet · MVSEC indoor2 (dt=4)AEE: 3.83 -> 4.05Hurt
increase number of event groups N from 2 to 4 (ablation)Spike-FlowNet · MVSEC indoor2 (dt=4)AEE: 3.83 -> 3.81No clear effect
raise smoothness weight lambda from 1 to 10 (ablation)Spike-FlowNet · MVSEC indoor2 (dt=1)AEE: 1.38 -> 1.28Improved
raise smoothness weight lambda from 1 to 10 (ablation)Spike-FlowNet · MVSEC indoor2 (dt=4)AEE: 3.83 -> 4.22Hurt
raise smoothness weight lambda from 1 to 100 (ablation)Spike-FlowNet · MVSEC indoor2 (dt=4)AEE: 3.83 -> 4.01Hurt
use hybrid SNN-encoder plus ANN architecture instead of fully ANN (EV-FlowNet)Spike-FlowNet · MVSEC indoor2 (dt=1)AEE: 1.72 -> 1.28Improved
use SNN encoder instead of ANN encoderSpike-FlowNet · MVSEC (mean of 4 sequences, dt=1)encoder compute energy: 214.2xImproved

Later papers that compared with this method

1 later accepted paper reports Spike-FlowNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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