To estimate 3D humans from video in world coordinates we add side information to prompt the process. Prompts include bounding boxes, face detections, segmentation masks, and text descriptions. It's currently the most accurate video-based method out there. See us at CVPR2025.
Michael J. Black
Next in our #CVPR2025 lineup: PromptHMR 👀💫
Turn any video into precise 3D people: occlusions, crowds, world coords solved. State of the art accuracy. 💯
Artists, devs, researchers get instant digital bodies.
Visit our booth 1333 @ CVPR to learn more about PromptHMR!
#AI #3D #DigitalHumans
