Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data

Abstract

Methods and datasets for human pose estimation focus predominantly on side- and front-view scenarios. We overcome the limitation by leveraging synthetic data and introduce RePoGen (RarE POses GENerator), an SMPL-based method for generating synthetic humans with comprehensive control over pose and view. Experiments on top-view datasets and a new dataset of real images with diverse poses show that adding the RePoGen data to the COCO dataset outperforms previous approaches to top- and bottom-view pose estimation without harming performance on common views. An ablation study shows that anatomical plausibility, a property prior research focused on, is not a prerequisite for effective performance. The introduced dataset and the corresponding code are available on https://mirapurkrabek.github.io/RePoGen-paper/ .

arXiv commenthttps://mirapurkrabek.github.io/RePoGen-paper/

References in corpus (7)

• Learning from Synthetic Humans
• ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
• Adding Conditional Control to Text-to-Image Diffusion Models
• Polarized Self-Attention: Towards High-quality Pixel-wise Regression
• PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision
• Unpaired Pose Guided Human Image Generation
• I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation

Cited by in corpus (1)

• WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users