Human motion generation aims to generate natural human pose sequences and shows
immense potential for real-world applications. Substantial progress has been made recently …

This work introduces MotionLCM, extending controllable motion generation to a real-time
level. Existing methods for spatial-temporal control in text-conditioned motion generation …

Abstract We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality
human motion generation. Current state-of-the-art generative diffusion models have …

In this paper, we present TMR, a simple yet effective approach for text to 3D human motion
retrieval. While previous work has only treated retrieval as a proxy evaluation metric, we …

Our goal is to synthesize 3D human motions given textual inputs describing simultaneous
actions, for examplewaving hand'whilewalking'at the same time. We refer to generating such …

This work targets a novel text-driven whole-body motion generation task, which takes a
given textual description as input and aims at generating high-quality, diverse, and coherent …

Given its wide applications, there is increasing focus on generating 3D human motions from
textual descriptions. Differing from the majority of previous works, which regard actions as …

Recent advancements in language models have demonstrated their adeptness in
conducting multi-turn dialogues and retaining conversational context. However, this …

The focus of this paper is 3D motion editing. Given a 3D human motion and a textual
description of the desired modification, our goal is to generate an edited motion as …

We introduce the M ulti-M otion D iscrete D iffusion M odels (M2D2M), a novel approach for
human motion generation from textual descriptions of multiple actions, utilizing the strengths …