AI Paper Atlas

Research map / Video / Video segmentation and tracking

Time Lens++: Event-Based Frame Interpolation With Parametric Non-Linear Flow and Multi-Scale Fusion

Stepan Tulyakov, Alfredo Bochicchio, Daniel Gehrig, Stamatios Georgoulis, Yuanyou Li, Davide Scaramuzza

CVPR 2022 · Video › Video segmentation and tracking · approach: Event-based video reconstruction · 7 citations (OpenAlex)

Check 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
replace linear motion with cubic spline flow (ablation)Time Lens++ motion module · Vimeo90k validationPSNR [dB]: 26.83 -> 27.41Improved
replace spline motion with non-parametric flow (ablation)Time Lens++ motion module · Vimeo90k validationPSNR [dB]: 27.41 -> 28.20Improved
replace spline motion with non-parametric flow (ablation)Time Lens++ motion module · 15 flow predictionsruntime [ms]: 220 -> 2700Hurt
add images to event-based motion estimation (ablation)Time Lens++ motion module · Vimeo90k validationPSNR [dB]: 26.82 -> 27.41Improved
add events to image-based motion estimation (ablation)Time Lens++ motion module · Vimeo90k validationPSNR [dB]: 24.51 -> 27.41Improved
combine synthesis and warping features (ablation)Time Lens++ fusion module · Vimeo90k validationPSNR [dB]: 29.77 -> 31.87Improved
add gated compression to feature fusion (ablation)Time Lens++ fusion module · Vimeo90k validationPSNR [dB]: 31.67 -> 31.87Improved
use separate image and event encoders instead of one U-Net (ablation)Time Lens++ motion module · Vimeo90k validationPSNR [dB]: 27.13 -> 27.41Improved
use multistage instead of single-stage training (ablation)Time Lens++ motion module · Vimeo90k validationPSNR [dB]: 27.41 -> 28.10Improved
share weights between the two synthesis encoders (ablation)Time Lens++ fusion module · Vimeo90k validationPSNR [dB]: 31.74 -> 31.87Improved
use multistage instead of single-stage training (ablation)Time Lens++ fusion module · Vimeo90k validationPSNR [dB]: 31.87 -> 32.73Improved
replace Time Lens fusion with multi-scale feature-level fusionTime Lens++ · Vimeo90k validationPSNR [dB]: 31.25 -> 32.73Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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