AI Paper Atlas

Research map / Video / Video generation

Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers

Xinyu Peng, Han Li, Yuyang Huang, Ziyang Zheng, Yaoming Wang, Xin Chen, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 1 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
add skip-concatenate sampling instead of causal AR order (ablation)LDF-VFI · SNU-FILM-entire (average)FVD: 22.67 -> 17.05Improved
add skip-concatenate sampling instead of causal AR order (ablation)LDF-VFI · SNU-FILM-entire (average)LPIPS: 0.062 -> 0.060Improved
add conditional VAE decoder over Wan2.1 decoder (ablation)LDF-VFI · SNU-FILM-entire (average)LPIPS: 0.060 -> 0.051Improved
add conditional VAE decoder over Wan2.1 decoder (ablation)LDF-VFI · SNU-FILM-entire (average)FVD: 17.05 -> 16.49Improved
add conditional VAE decoder over Wan2.1 decoder (ablation)LDF-VFI · SNU-FILM-entire 8xFVD: 14.55 -> 15.01Hurt
use sparse attention instead of full attention (ablation)LDF-VFI · X4K-entire 16xFVD: 772.32 -> 120.40Improved
use sparse attention instead of full attention (ablation)LDF-VFI · SNU-FILM-entire 8xrunning time (s): 4.68 -> 3.36Improved
use nearest-neighbor upsampling instead of zero padding (ablation)LDF-VFI · SNU-FILM-4x key-frame VAE reconstructionPSNR: 28.40 -> 30.87Improved
use temporal chunk length 20 instead of 5 (ablation)LDF-VFI · X4K-entire 16xFVD: 510.63 -> 121.29Improved
use temporal chunk length 20 instead of 5 (ablation)LDF-VFI · SNU-FILM-entire 8xLPIPS: 0.059 -> 0.066Hurt
increase sampling steps from 2 to 16LDF-VFI · SNU-FILM-entire 8xFVD: 21.25 -> 15.01Improved

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