AI Paper Atlas

Research map / Video / Video generation

Realtime Video Frame Interpolation using One-Step Diffusion Sampling

Yongrui Ma, Shijie Zhao, Mingde Yao, Junlin Li, Li zhang, Xiaohong Liu, Qi Dou, Jinwei Gu, Tianfan Xue

ICLR 2026 · Video › Video generation · approach: Efficient video diffusion models

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 iterative flow fusion for continuous pixel trajectories (vs Direct Warping) (ablation)RDVFI-D · ablation set (Table 3b)FVD: 327.11 -> 209.38Improved
add iterative flow fusion (vs Direct Warping) (ablation)RDVFI-D · ablation set (Table 3b)FID: 42.33 -> 23.71Improved
add pixel-space perceptual loss (vs L+P-L2 loss) (ablation)RDVFI-D · ablation set (Table 3b)FVD: 267.42 -> 209.38Improved
add pixel-wise reconstruction losses (L loss vs L+P-L2 loss) (ablation)RDVFI-D · ablation set (Table 3b)FVD: 281.37 -> 267.42Improved
use motion-guided decoding with fixed low-resolution diffusion (vs one-step Wan) (ablation)RDVFI-D · 1024x576runtime (ms): 267.7 -> 58.01Improved
raise output resolution from 576x320 to 1280x720 (ablation)RDVFI-D · runtime scalingruntime (ms): 55.3 -> 63.49No clear effect
raise output resolution from 576x320 to 1280x720 (ablation)one-step Wan · runtime scalingruntime (ms): 103.3 -> 314.3Hurt
use DiT backbone Wan (RDVFI-D) instead of SVD U-Net (RDVFI-U) (ablation)RDVFI · FCVG datasetFVD: 217.72 -> 197.86Improved
use RDVFI-D instead of Wan with same backboneWan 1.3B InP · FCVG datasetruntime (sec): 2.579 -> 0.057Improved
use RDVFI-D instead of RIFERIFE · FCVG datasetFVD: 366.14 -> 197.86Improved
use RDVFI-D instead of WanWan · human evaluation, overallshare choosing as best (%): 14.2% -> 75.7%Improved
increase frame skip to 7 so input frames barely overlapRDVFI · failure caseinterpolation qualityHurt

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