AI Paper Atlas

Research map / Video / Video generation

OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Based Video Editing

Haoyang He, Jie Wang, Jiangning Zhang, Zhucun Xue, Xingyuan Bu, Qiangpeng Yang, Min Zheng, Lei Xie

ECCV 2026 · Video › Video generation · approach: Diffusion-based video editing

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
jointly feed video and instruction into an MLLM in addition to umT5 (ablation)OpenVE-Edit · OpenVE-Bench (Seed1.6-VL judge)overall score: 2.12 to 2.31Improved
add MoE-Connector over a shared-parameter connector (ablation)OpenVE-Edit · OpenVE-Bench (Seed1.6-VL judge)overall score: 2.31 to 2.41Improved
train on OpenVE-3M instead of Senorita-2M (ablation)OpenVE-Edit · OpenVE-Bench (Seed1.6-VL judge)overall score: 1.54 to 2.41Improved
use Canny edge control instead of depth control in data generation (ablation)Wan2.1-Fun-Control data pipeline · data constructionqualitative detailImproved
replace FlashAttention-2 with SageAttention-2 and cut steps from 50 to 10 (ablation)Wan2.1-Fun-V1.1-14B-Control data generation · data constructiongeneration time: 50 minutes to 6 minutesImproved
use MiniMax-Remover instead of DiffuEraser (ablation)video removal data generation · data constructioninference time and consistency: twice the inference timeMixed
score data with Seed1.6-VL rather than Qwen3-VL-30B-A3B as judge (ablation)OpenVE-Bench · human alignmentPLCC: 0.583 to 0.833Improved
OpenVE-Edit (5B) versus 14B open-source baselinesOpenVE-Edit · OpenVE-Bench (Seed1.6-VL judge)overall score: 2.41 vs 2.24Improved

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