AI Paper Atlas

Research map / Video / Video segmentation and tracking

Optimizing Video Prediction via Video Frame Interpolation

Yue Wu, Qiang Wen, Qifeng Chen

CVPR 2022 · Video › Video segmentation and tracking · approach: Video frame interpolation · 53 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
Use VFI-constrained optimization without external video-prediction trainingVideo prediction · Cityscapes, t+1MS-SSIM (×1e-2): 89.10 -> 94.54Improved
Use VFI-constrained optimization without external video-prediction trainingVideo prediction · KITTI, t+1LPIPS (×1e-2): 18.48 -> 12.34Improved
Use VFI-constrained optimization without external video-prediction trainingVideo prediction · DAVIS, t+1LPIPS (×1e-2): 13.09 -> 11.40Improved
Use VFI-constrained optimization without external video-prediction trainingVideo prediction · Middlebury, t+1LPIPS (×1e-2): 7.98 -> 6.07Improved
Use VFI-constrained optimization without external video-prediction trainingVideo prediction · Vimeo90K, t+1LPIPS (×1e-2): 7.73 -> 3.59Improved
Add the image loss to the consistency loss (ablation)Full video-prediction method · Cityscapes, t+1SSIM: 0.8939 -> 0.8975Improved
Add the consistency loss to the image loss (ablation)Full video-prediction method · Cityscapes, t+1SSIM: 0.8732 -> 0.8975Improved
Replace L1 image loss with MSE (ablation)Full video-prediction method · Cityscapes, t+1SSIM: 0.8975 -> 0.8877Hurt
Use the VFI intermediate output instead of the final interpolation result (ablation)Full video-prediction method · Cityscapes, t+1SSIM: 0.8975 -> 0.8963No clear effect
Add a long-term image constraint using four input frames (ablation)Full video-prediction method · Cityscapes, t+1SSIM: 0.8975 -> 0.6978Hurt
Add optical-flow inpainting (ablation)Full video-prediction method · Cityscapes, t+1SSIM: 0.8882 -> 0.8975Improved
Initialize optical flow with zero values or Gaussian noise instead of a motion-based initialization (ablation)Full video-prediction method · Cityscapes, t+1SSIM: 0.8975 -> 0.7719; 0.8975 -> 0.7669Hurt

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