AI Paper Atlas

Research map / Video / Video generation

Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models

Yixuan Ren, Yang Zhou, Jimei Yang, Jing Shi, Difan Liu, Feng Liu, Mingi Kwon, Abhinav Shrivastava

ECCV 2024 · Video › Video generation · approach: Efficient video diffusion models · 50 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 TextInv appearance absorber before training Temporal LoRA (ablation)Customize-A-Video (T-LoRA) · LOVEU-TGVE subsettext alignment (CLIPScore): 31.687 -> 32.632Improved
add S-LoRA appearance absorber before training Temporal LoRA (ablation)Customize-A-Video (T-LoRA) · LOVEU-TGVE subsettext alignment (CLIPScore): 31.687 -> 31.913Improved
use dual appearance absorbers (S-LoRA + TextInv) instead of single (ablation)Customize-A-Video · LOVEU-TGVE subsetdiversity (LPIPS): 0.621 -> 0.631Improved
use dual appearance absorbers instead of TextInv only (ablation)Customize-A-Video · LOVEU-TGVE subsettext alignment (CLIPScore): 32.632 -> 32.193Hurt
apply LoRA on spatial attention (S-LoRA or ST-LoRA) instead of temporal attention only (ablation)motion LoRA · qualitative ablationmotion modelingHurt
use T-LoRA with appearance absorber instead of ModelScope text prompt onlyModelScope T2V · LOVEU-TGVE subsetdiversity (LPIPS): 0.636 -> 0.621Hurt
use Customize-A-Video instead of Tune-A-Video/Video-P2P without DDIM inversionone-shot motion customization · LOVEU-TGVE subsetdiversity (LPIPS): 0.348 -> 0.621 (Tune-A-Video w/o DDIM)Improved
use Customize-A-Video instead of MotionDirectorone-shot motion customization · user studymotion fidelity: 3.33 -> 3.72Improved
use Customize-A-Video instead of MotionDirectorone-shot motion customization · LOVEU-TGVE subsetdiversity (LPIPS): 0.606 -> 0.621Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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