AI Paper Atlas

Research map / Video / Video generation

DIVE: Taming DINO for Subject-Driven Video Editing

Yi Huang, Wei Xiong, He Zhang, Chaoqi Chen, Jianzhuang Liu, Mingfu Yan, Shifeng Chen

ICCV 2025 · Video › Video generation · approach: Diffusion-based video editing · 11 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 DINO motion guidance instead of fine-tuned motion module only (ablation)DIVE · Reference-image-guided subject editing (30 videos)Image alignment: 67.49 -> 84.27Improved
add DINO motion guidance instead of fine-tuned motion module only (ablation)DIVE · Reference-image-guided subject editing (30 videos)Overall video quality: 0.737 -> 0.775Improved
add DINO motion guidance instead of fine-tuned motion module only (ablation)DIVE · Reference-image-guided subject editing (30 videos)Text alignment: 29.91 -> 29.43Hurt
raise guidance weight lambda from 0 to 1.0 (frozen motion module) (ablation)DIVE · Reference-image-guided subject editing (30 videos)Temporal consistency: 87.24 -> 92.33Improved
raise guidance weight lambda from 0.3 to 1.0 (ablation)DIVE · Reference-image-guided subject editing (30 videos)Overall video quality: 0.628 -> 0.775Improved
raise guidance weight lambda from 0 to 1.0 (ablation)DIVE · Reference-image-guided subject editing (30 videos)Overall video quality: 0.581 -> 0.775Improved
add DINO features to identity registration (ablation)DIVE · Reference-image-guided subject editing (30 videos)Image alignment: 77.36 -> 84.27Improved
add DINO features to identity registration (ablation)DIVE · Reference-image-guided subject editing (30 videos)Overall video quality: 0.722 -> 0.775Improved
add DINO features to identity registration (ablation)DIVE · Reference-image-guided subject editing (30 videos)Temporal consistency: 92.12 -> 92.33No clear effect
use DIVE instead of FLATTEN (best baseline) for reference-image editingDIVE · Reference-image-guided subject editing (30 videos)Overall video quality: 0.683 -> 0.775Improved
use DIVE instead of AnyV2V for reference-image editingDIVE · Reference-image-guided subject editing (30 videos)Image alignment: 78.26 -> 84.27Improved
use DIVE instead of RAVE for text-guided editingDIVE · Text-guided subject editing (30 videos)Temporal consistency: 95.12 -> 95.89Improved

Later papers that compared with this method

1 later accepted paper reports DiVE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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