Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space
Yuan Wang, Zhao Wang, Junhao Gong, Di Huang, Tong He, Wanli Ouyang,, Jile Jiao, Xuetao Feng, Qi Dou, Shixiang Tang, Dan Xu

TL;DR
This paper introduces Holistic-Motion2D, a large-scale 2D human motion dataset and a baseline method Tender, enabling scalable, diverse, and realistic whole-body motion generation from 2D data, with potential for 3D lifting.
Contribution
It presents the first comprehensive 2D motion dataset and a novel attention-based baseline method for 2D whole-body human motion generation.
Findings
Holistic-Motion2D contains over 1 million motion sequences, ten times larger than previous 3D datasets.
Tender effectively generates expressive, diverse, and realistic 2D human motions.
The approach demonstrates utility in downstream applications and potential for 3D motion lifting.
Abstract
In this paper, we introduce a novel path to human motion generation by focusing on 2D space. Traditional methods have primarily generated human motions in 3D, which, while detailed and realistic, are often limited by the scope of available 3D motion data in terms of both the size and the diversity. To address these limitations, we exploit extensive availability of 2D motion data. We present , the first comprehensive and large-scale benchmark for 2D whole-body motion generation, which includes over 1M in-the-wild motion sequences, each paired with high-quality whole-body/partial pose annotations and textual descriptions. Notably, Holistic-Motion2D is ten times larger than the previously largest 3D motion dataset. We also introduce a baseline method, featuring innovative and $\textit{confidence-aware…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Pose and Action Recognition · Human Motion and Animation · Robotic Locomotion and Control
