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

Gregory Rogez 1 Cordelia Schmid 1
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [43 references]  Display  Hide  Download


https://hal.inria.fr/hal-01389486
Contributor : Gregory Rogez <>
Submitted on : Tuesday, August 1, 2017 - 10:48:34 AM
Last modification on : Friday, October 5, 2018 - 6:15:23 PM

Files

nips_2016_ext.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01389486, version 1

Collections

Citation

Gregory Rogez, Cordelia Schmid. MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild. Advances in Neural Information Processing Systems (NIPS), Dec 2016, Barcelona, Spain. pp.3108-3116. ⟨hal-01389486⟩

Share

Metrics

Record views

649

Files downloads

5253