AI Paper Atlas

Research map / Video / Video generation

Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models

Qinyu Yang, Haoxin Chen, Yong Zhang, Menghan Xia, Xiaodong Cun, Zhixun Su, Ying Shan

ECCV 2024 · Video › Video generation · approach: Diffusion-based video editing · 2 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 Noise Calibration (2 iterations) to SDEditSDEdit with VideoCrafter · Lavie700 enhancementMSE_l: 4.3447 -> 2.8039Improved
add Noise Calibration (2 iterations) to SDEditSDEdit with VideoCrafter · Lavie700 enhancementDOVER: 60.17 -> 62.71Improved
add Noise Calibration to SDEditSDEdit with VideoCrafter · Lavie700 enhancementCLIP-IQA: 0.4482 -> 0.4387Hurt
increase calibration iterations from 3 to 10 (ablation)NC-SDEdit · Lavie700 enhancementDOVER: 62.45 -> 54.42Hurt
increase calibration iterations from 1 to 2 (ablation)NC-SDEdit · Lavie700 enhancementDOVER: 60.62 -> 62.71Improved
increase threshold frequency from 0.0 to 1.0 (ablation)NC-SDEdit (t0=600) · 60 videoslow-frequency L2 (lower better): 4.2997 -> 2.7957Improved
increase initial denoising step t0 from 500 to 700 (ablation)NC-SDEdit (nu=1.0) · 60 videoscontent consistency vs detail: 2.0706 -> 3.9010 (L2), 0.0641 -> 0.0664 (D_SF)Mixed
add Noise Calibration to MS-Vid2Vid-XLMS-Vid2Vid-XL · EvalCrafter 700 videosDOVER: 52.89 -> 57.61Improved
add Noise Calibration to SDXL-1.0-refinerSDXL-1.0-refiner · SDXL images from 700 textsMSE_l: 1.2775 -> 0.8750Improved
add Noise Calibration to SDEdit, inference costSDEdit · inference timeadditional inference time: less than 10% additionalNo clear effect

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