AI Paper Atlas

Research map / Video / Video generation

FiVE-Bench: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models

Minghan Li, Chenxi Xie, Yichen Wu, Lei Zhang, Mengyu Wang

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 22 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
replace diffusion-based editing with RF-based Wan-Edit (inversion-free FlowEdit)video editing · FiVE benchmarktime per frame (s): 27.12 -> 3.07Improved
use Wan-Edit instead of VideoGrain for background preservationWan-Edit · FiVE benchmarkLPIPS x10^3: 185.21 -> 94.61Improved
use Wan-Edit instead of VideoGrain for PSNR/MSEWan-Edit · FiVE benchmarkPSNR: 27.05 -> 25.57Hurt
CLIP score as editing-quality metric versus VLM-based FiVE-Accevaluation metrics · FiVE benchmarkmetric discriminability: TokenFlow 27.43 vs DMT 48.42 FiVE-Acc despite close CLIP scoresImproved
RF-based Wan-Edit versus feature-propagation methods on non-rigid editsWan-Edit · FiVE Edit2 (non-rigid)FiVE-Acc (%): 52.02 -> 52.02 (Wan-Edit stable) while DMT 67.86 -> 53.72Improved
use Pyramid-Edit's multi-resolution autoregressive architecturePyramid-Edit · FiVE benchmarkqualitative edit qualityHurt
Wan-Edit versus Pyramid-Edit on object additionRF-based editing · FiVE Edit5 (object addition)FiVE-Acc (%): DMT 61% vs Pyramid-Edit 83%, Wan-Edit 72%Improved
object removal editing with current methodsall methods · FiVE Edit6 (object removal)FiVE-Acc: below 20%Hurt
Qwen-2.5-VL evaluator replacing human evaluator (ablation)FiVE-Acc · FiVE human validationFiVE-Acc (%): 47.34 -> 46.97No clear effect
propagating tokens via feature clustering (TokenFlow, VidToMe)TokenFlow, VidToMe · FiVE benchmarkFiVE-Acc (%): 27.43 and 26.77 vs 48.42 for DMTHurt

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