AI Paper Atlas

Research map / Video / Video generation

EasyV2V: A High-quality Instruction-based Video Editing Framework

Jinjie Mai, Chaoyang Wang, Gordon Guocheng Qian, Willi Menapace, Sergey Tulyakov, Bernard Ghanem, Peter Wonka, Ashkan Mirzaei

CVPR 2026 · Video › Video generation · approach: Diffusion-based video editing · 7 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
use sequence concatenation instead of embedding addition for source video (ablation)EasyV2V with LoRA · EditVerse architecture ablationVLM score @ 40K: 6.29 -> 7.47Improved
use LoRA instead of full finetuning (ablation)EasyV2V with SeqCat · EditVerse architecture ablationVLM score @ 40K: 3.94 -> 7.47Improved
use LoRA instead of full finetuning (ablation)EasyV2V with EmbedAdd · EditVerse architecture ablationVLM score @ 40K: 4.57 -> 6.29Improved
add affine-transformed I2I pairs as pseudo videos to single-image I2I (ablation)V2V editor · I2I data ablationVLM edit quality: 5.52 -> 6.24Improved
add I2I data (single + affine) to V2V training data (ablation)V2V editor · I2I data ablationVLM edit quality: 6.69 -> 6.86Improved
train on Human Animate vs Actor Transmutation (Flow Edit) data (ablation)V2V editor · Dataset ablation, Actor transmutationVLM score: 7.20 -> 8.30Hurt
add dense-caption data for human action edits (ablation)V2V editor · Dataset ablation, Change human actionVLM score: 4.97 -> 6.87Improved
add stylization data (ablation)V2V editor · Dataset ablation, StylizationVLM score: 4.97 -> 7.97Improved
inject mask by addition into source latent instead of Wan VACE branch (ablation)mask control · Mask conditioning comparisonVLM score (average): 5.50 -> 7.48Improved
inject mask into source latent instead of target latent (ablation)mask control · Mask conditioning comparisonVLM score (average): 6.45 -> 7.48Improved
raise LoRA rank from 64 to 256 (ablation)EasyV2V · EditVerse LoRA rankVLM quality score (w/o Ref.): 6.17 -> 6.48Improved
add reference image from an image editor (ablation)EasyV2V rank 256 · EditVerse LoRA rankVLM quality score: 6.48 -> 7.22Improved

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