AI Paper Atlas

Research map / Video / Video generation

Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis

Rishabh Dabral, Muhammad Hamza Mughal, Vladislav Golyanik, Christian Theobalt

CVPR 2023 · Video › Video generation · approach: Text-to-motion diffusion · 153 citations (OpenAlex)

Read the paper

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
Use MoFusion instead of Bailando for music-conditioned motion synthesisMusic-to-dance synthesis · AIST++ testBAS: 0.233 -> 0.253Improved
Use MoFusion instead of Bailando for music-conditioned motion synthesisMusic-to-dance synthesis · AIST++ testFID: 28.16 -> 50.31Hurt
Use MoFusion instead of Bailando for music-conditioned motion synthesisMusic-to-dance synthesis · AIST++ testDiversity: 7.83 -> 9.09Improved
Use MoFusion instead of Guo et al.'s method for text-conditioned synthesisText-to-motion synthesis · HumanML3DMulti-Modality: 2.090 -> 2.521Improved
Use MoFusion instead of Guo et al.'s method for text-conditioned synthesisText-to-motion synthesis · HumanML3DR-Precision: 0.740 -> 0.492Hurt
Use MoFusion instead of Guo et al.'s method for text-conditioned synthesisText-to-motion synthesis · HumanML3DDiversity: 9.188 -> 8.82Hurt

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