AI Paper Atlas

Research map / Video / Video generation

M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models

Seunggeun Chi, Hyung-gun Chi, Hengbo Ma, Nakul Agarwal, Faizan Siddiqui, Karthik Ramani, Kwonjoon Lee

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 21 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
use dynamic transition probability beta(t,d) instead of static beta_t (ablation)M2D2M · HumanML3D single-motionFID: 0.115 -> 0.087Improved
use dynamic transition probability beta(t,d) (ablation)M2D2M · KIT-ML single-motionFID: 0.404 -> 0.378Improved
use Two-Phase Sampling instead of Handshake (ablation)VQ-Diffusion multi-motion · HumanML3D multi-motionindividual FID: 1.279 -> 0.254Improved
use Two-Phase Sampling instead of SLERP (ablation)VQ-Diffusion multi-motion · HumanML3D multi-motionindividual FID: 1.402 -> 0.254Improved
reduce joint sampling steps Ts from 100 to 90 (with dynamic probability) (ablation)M2D2M · HumanML3D multi-motionindividual FID: FID 0.196 -> 0.253; transition Jerk 1.248 -> 1.238Mixed
M2D2M vs T2M-GPT on KIT-ML transition qualityM2D2M · KIT-ML multi-motion transitionFID: T2M-GPT 14.494 vs M2D2M 15.843Hurt
M2D2M vs M2DM on single-motion diversity of outputsM2D2M · HumanML3D single-motionMModality: 3.587 vs 2.115Hurt

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