WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users
William Huang, Sam Ghahremani, Siyou Pei, Yang Zhang

TL;DR
This paper introduces a data synthesis pipeline using Unity to generate realistic, diverse synthetic datasets of wheelchair users, significantly improving pose estimation models' performance and inclusiveness for this underrepresented group.
Contribution
The authors present a configurable Unity-based data synthesis pipeline that enhances pose estimation for wheelchair users by generating realistic, diverse synthetic datasets, addressing data scarcity and bias.
Findings
Synthetic datasets are perceived as realistic by humans.
Fine-tuning on synthetic data improves pose estimation accuracy.
Generated datasets exhibit greater diversity than existing datasets.
Abstract
Existing pose estimation models perform poorly on wheelchair users due to a lack of representation in training data. We present a data synthesis pipeline to address this disparity in data collection and subsequently improve pose estimation performance for wheelchair users. Our configurable pipeline generates synthetic data of wheelchair users using motion capture data and motion generation outputs simulated in the Unity game engine. We validated our pipeline by conducting a human evaluation, investigating perceived realism, diversity, and an AI performance evaluation on a set of synthetic datasets from our pipeline that synthesized different backgrounds, models, and postures. We found our generated datasets were perceived as realistic by human evaluators, had more diversity than existing image datasets, and had improved person detection and pose estimation performance when fine-tuned on…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGaze Tracking and Assistive Technology · Spinal Cord Injury Research · Stroke Rehabilitation and Recovery
MethodsSparse Evolutionary Training
