AI Paper Atlas

Research map / Video / Video generation

DNI: Dilutional Noise Initialization for Diffusion Video Editing

Sunjae Yoon, Gwanhyeong Koo, Ji Woo Hong, Chang D. Yoo

ECCV 2024 · 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
apply DNI noise dilution to existing video editorsTAV, FateZero, Video-P2P, TokenFlow · DAVIS/TGVE non-rigid editingCLIP text-video: TAV 22.6 -> 27.6; TF 21.7 -> 25.9Improved
apply DNI to rigid editingTokenFlow · DAVIS/TGVE rigid editingSSIM: 0.677 -> 0.733Improved
apply DNI to FateZero fidelity (non-rigid LPIPS)FateZero · DAVIS/TGVE non-rigid editingLPIPS: 0.173 -> 0.168No clear effect
use adaptive spectral filter instead of Gaussian low-pass filters to extract visual noise (ablation)DNI noise disentanglement · visual noise extractionPSNR: 13.2 -> 18.4Improved
use only the noise branch (drop visual branch) (ablation)DNI · qualitative thumbs-up promptfidelityHurt
use visual branch without dilution (ablation)DNI · qualitative thumbs-up promptnon-rigid edit qualityHurt
raise rigid mask scaler alpha above 0.7 (ablation)DNI · rigid editing sensitivitytextual alignmentHurt
increase non-rigid mask scaler beta (ablation)DNI · non-rigid editing sensitivityedit synthesisImproved

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