SSP-Net: Scalable Sequential Pyramid Networks for Real-Time 3D Human Pose Regression

4 Sep 2020  ·  Diogo Luvizon, Hedi Tabia, David Picard ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M SSP-Net Average MPJPE (mm) 50.2 # 167
3D Human Pose Estimation MPI-INF-3DHP SSP-Net AUC 44.3 # 56
MPJPE 96.8 # 60
PCK 83.2 # 51

Methods


No methods listed for this paper. Add relevant methods here