AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video Frame Interpolation without Temporal Priors

Youjian Zhang, Chaoyue Wang, Dacheng Tao

NeurIPS 2020 · Video › Video segmentation and tracking · approach: Video frame interpolation · 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
Use the proposed full method instead of the strongest reported baselineVideo frame interpolation · GoPro-5-5, GoPro-7-3, GoPro-9-1 and Adobe240-5-5, Adobe240-7-3, Adobe240-9-1interpolation PSNR: GoPro: 32.47 vs 29.13; 31.95 vs 30.92; 30.95 vs 30.82. Adobe240: 31.79 vs 29.5; 31.52 vs 31.43; 30.66 vs 30.48Improved
Use uncertain-time-interval motion interpolation rather than QVI with λ=1Sharp-frame interpolation · GoPro, λ=7/3 and λ=9/1PSNR: 32.35 -> 32.65; 29.17 -> 29.75Improved
Add optical flow refinement to UTI (ablation)Sharp-frame interpolation · GoPro, λ=7/3 and λ=9/1PSNR: 32.65 -> 33.56; 29.75 -> 30.57Improved
Add second-order residual learning (ablation)Key-state restoration · GoPro-5-5, GoPro-7-3, GoPro-9-1PSNR: 32.39 -> 34.00; 31.15 -> 32.63; 30.38 -> 31.72Improved
Cascade another stage-I architecture without B1 and B2 as inputs (ablation)Key-state restoration · GoPro-5-5, GoPro-7-3, GoPro-9-1PSNR: 34.00 vs 32.49; 32.63 vs 31.41; 31.72 vs 30.76Hurt
Use only 2 input frames instead of the proposed input structure (ablation)Key-state restoration · GoPro-5-5, GoPro-7-3, GoPro-9-1PSNR: 34.00 vs 33.07; 32.63 vs 31.83; 31.72 vs 30.74Hurt
Remove optical flow refinement (ablation)Interpolation · GoPro-5-5, GoPro-7-3, GoPro-9-1PSNR: 31.82 -> 32.47; 31.34 -> 31.95; 30.3 -> 30.95Hurt
Apply the equal-interval QVI trajectory when time intervals are unevenSharp-frame interpolation · GoPro, λ=7/3 and λ=9/1PSNR: 32.65 vs 32.35; 29.75 vs 29.17Hurt
Iteratively synthesize the middle frame for TNTT* under exposure setting 5-5TNTT* · GoPro-5-5 interpolationPSNR: 32.49 -> 28.39Hurt
Use a cascade of deblurring followed by interpolationCascade models · GoPro and Adobe240 blurry video interpolationPSNR: about 3 dB lossHurt

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