Synthesizing Training Images for Boosting Human 3D Pose Estimation

Citations Over TimeTop 1% of 2016 papers

Abstract

Human 3D pose estimation from a single image is a challenging task with numerous applications. Convolutional Neural Networks (CNNs) have recently achieved superior performance on the task of 2D pose estimation from a single image, by training on images with 2D annotations collected by crowd sourcing. This suggests that similar success could be achieved for direct estimation of 3D poses. However, 3D poses are much harder to annotate, and the lack of suitable annotated training images hinders attempts towards end-to-end solutions. To address this issue, we opt to automatically synthesize training images with ground truth pose annotations. Our work is a systematic study along this road. We find that pose space coverage and texture diversity are the key ingredients for the effectiveness of synthetic training data. We present a fully automatic, scalable approach that samples the human pose space for guiding the synthesis procedure and extracts clothing textures from real images. Furthermore, we explore domain adaptation for bridging the gap between our synthetic training images and real testing photos. We demonstrate that CNNs trained with our synthetic images out-perform those trained with real photos on 3D pose estimation tasks.

Related Papers

• → Learning to Refine Human Pose Estimation(2018)112 cited
• → Fast 6D object pose estimation of shell parts for robotic assembly(2021)7 cited
• → SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space(2022)3 cited
• → Fast 6D Object Pose Estimation of Shell Parts for Robotic Assembly(2021)1 cited
• → Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose\n Estimation(2020)