AI Paper Atlas

Research map / Video / Video generation

Towards Consistent Video Editing with Text-to-Image Diffusion Models

Zicheng Zhang, Bonan Li, Xuecheng Nie, Congying Han, Tiande Guo, Luoqi Liu

NeurIPS 2023 · 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
Replace Layer Norm in temporal attention with Instance Centering (about 20% faster than Instance Norm) (ablation)EI^2 temporal attention · Video editingcomputational speed: about 20%Improved
Replace Layer Norm in Tune-A-Video TA module with Instance Norm (ablation)Tune-A-Video · Video editingtextual guidance (qualitative)Improved
Remove rescaling parameters of Layer Norm or remove the module (ablation)Tune-A-Video · Video editingcovariate shift / editing (qualitative)No clear effect
Add Instance Centering and weight (spectral) normalization (ablation)EI^2 STAM · Video editingediting quality (qualitative)Improved
Replace SCA with FFAM in combination with STAM (ablation)EI^2 · Video editingtemporal consistency (qualitative)Improved
Full spatial-temporal attention over 8 frames instead of FFAM (ablation)EI^2 · Video editingmemory and training time: 32GiB; ~45minHurt
Use EI^2 instead of Tune-A-VideoTune-A-Video · Textual alignmentCLIP score: 28.72 -> 29.84Improved
Use EI^2 instead of Tune-A-VideoTune-A-Video · Frame consistencyCLIP score: 96.64 -> 95.94Hurt
Use EI^2 instead of Tune-A-VideoTune-A-Video · Textual alignmentuser vote: 15.4\% -> 42.7\%Improved
Use EI^2 instead of Tune-A-VideoTune-A-Video · Frame consistencyuser vote: 25.6\% -> 34.9\%Improved
EI^2 training overhead vs Tune-A-VideoTune-A-Video · Training runtimeminutes: 11.0 -> 12.5Hurt
Insert STAM before vs after CA module (ablation)EI^2 · Video editingvisual quality (qualitative)No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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