Visual Results
[1] Guo et al. Generating diverse and natural 3d human motions from text. CVPR, 2022.
[2] Tevet et al. Human motion diffusion model. arXiv, 2022.
[3] Zhang et al. Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv, 2022.
Text Prompting: a man steps forward and does a handstand.
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: A man rises from the ground, walks in a circle and sits back down on the ground.
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: a person jogs in place, slowly at first, then increases speed. they then back up and squat down.
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: a man starts off in an up right position with botg arms extended out by his sides, he then brings his arms down to his body and claps his hands together. after this he wals down amd the the left where he proceeds to sit on a seat
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: a person puts their hands together, leans forwards slightly then swings the arms from right to left
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: someone appears to be stretching they turn their upper body in a counter clockwise direction and then leans upper body from side to side
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: moving sideways then stopping.
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: a person uses their left knee to get up from the floor.
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: a man is practicing the waltz with a partner
T2M [1]
MDM [2]
MotionDiffuse [3]
Text Prompting: a person is playing jumprope.
T2M [1]
MDM [2]
MotionDiffuse [3]
© This webpage was in part inspired from this
template.
