MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild

TL;DR

This paper introduces a novel image synthesis engine that augments real datasets with photorealistic images generated from 3D MoCap data, significantly improving 3D human pose estimation in wild images.

Contribution

The authors propose a new MoCap-guided image synthesis method to create large, diverse training datasets for CNNs, enhancing 3D pose estimation accuracy in real-world scenarios.

Findings

Outperforms state-of-the-art on Human3.6M dataset

Shows promising results on in-the-wild LSP dataset

Demonstrates CNN generalization from synthetic to real images

Abstract

This paper addresses the problem of 3D human pose estimation in the wild. A significant challenge is the lack of training data, i.e., 2D images of humans annotated with 3D poses. Such data is necessary to train state-of-the-art CNN architectures. Here, we propose a solution to generate a large set of photorealistic synthetic images of humans with 3D pose annotations. We introduce an image-based synthesis engine that artificially augments a dataset of real images with 2D human pose annotations using 3D Motion Capture (MoCap) data. Given a candidate 3D pose our algorithm selects for each joint an image whose 2D pose locally matches the projected 3D pose. The selected images are then combined to generate a new synthetic image by stitching local image patches in a kinematically constrained manner. The resulting images are used to train an end-to-end CNN for full-body 3D pose estimation. We cluster the training data into a large number of pose classes and tackle pose estimation as a K-way classification problem. Such an approach is viable only with large training sets such as ours. Our method outperforms the state of the art in terms of 3D pose estimation in controlled environments (Human3.6M) and shows promising results for in-the-wild images (LSP). This demonstrates that CNNs trained on artificial images generalize well to real images.