SSP-Net: Scalable Sequential Pyramid Networks for Real-Time 3D Human Pose Regression
This addresses the need for fast and accurate 3D pose estimation in applications like robotics or AR, but it is incremental as it builds on existing regression methods with scalability improvements.
The paper tackles real-time 3D human pose regression from RGB images by proposing SSP-Net, achieving up to 200 FPS with results comparable to state-of-the-art on datasets like Human3.6M and MPI-INF-3DHP.
In this paper we propose a highly scalable convolutional neural network, end-to-end trainable, for real-time 3D human pose regression from still RGB images. We call this approach the Scalable Sequential Pyramid Networks (SSP-Net) as it is trained with refined supervision at multiple scales in a sequential manner. Our network requires a single training procedure and is capable of producing its best predictions at 120 frames per second (FPS), or acceptable predictions at more than 200 FPS when cut at test time. We show that the proposed regression approach is invariant to the size of feature maps, allowing our method to perform multi-resolution intermediate supervisions and reaching results comparable to the state-of-the-art with very low resolution feature maps. We demonstrate the accuracy and the effectiveness of our method by providing extensive experiments on two of the most important publicly available datasets for 3D pose estimation, Human3.6M and MPI-INF-3DHP. Additionally, we provide relevant insights about our decisions on the network architecture and show its flexibility to meet the best precision-speed compromise.