AI Paper Atlas

Research map / Video / Video generation

SMooDi: Stylized Motion Diffusion Model

Lei Zhong, Yiming Xie, Varun Jampani, Deqing Sun, Huaizu Jiang

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 52 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 cycle prior-preservation loss (ablation)SMooDi · Stylized text2motionFID: 2.046 -> 1.609Improved
add content prior-preservation loss (with cycle loss) (ablation)SMooDi · Stylized text2motionFID: 5.996 -> 2.046Improved
add classifier-based style guidance (ablation)SMooDi · Stylized text2motionSRA (%): 20.245 -> 72.418Improved
add classifier-based style guidance (ablation)SMooDi · Stylized text2motionFID: 1.050 -> 1.609Hurt
add content-aware style adaptor (ablation)SMooDi · Stylized text2motionFID: 2.984 -> 1.609Improved
generate stylized motion with SMooDi instead of MLD plus style transferSMooDi · Stylized text2motionSRA: 63.769 -> 72.418Improved
describe style in text via ChatGPT instead of a style motionMLD · Stylized text2motionSRA: 72.418 -> 4.819Hurt
use SMooDi via DDIM inversion for style transfer instead of dedicated transfer methodsSMooDi · Xia dataset style transferSRA (%): 67.778 -> 61.111 (SRA), 25.556 -> 45.555 (CRA)Mixed

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