Light3DPose: Real-time Multi-Person 3D Pose Estimation from Multiple Views
| Autor: | Alessio Elmi, Davide Mazzini, Pietro Tortella |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
business.industry Estimator Inference 02 engineering and technology Solid modeling 010501 environmental sciences 3D pose estimation 01 natural sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Transfer of learning Representation (mathematics) Pose Decoding methods 0105 earth and related environmental sciences |
| Zdroj: | ICPR |
| Popis: | We present an approach to perform 3D pose estimation of multiple people from a few calibrated camera views. Our architecture, leveraging the recently proposed unprojection layer, aggregates feature-maps from a 2D pose estimator backbone into a comprehensive representation of the 3D scene. Such intermediate representation is then elaborated by a fully-convolutional volumetric network and a decoding stage to extract 3D skeletons with sub-voxel accuracy. Our method achieves state of the art MPJPE on the CMU Panoptic dataset using a few unseen views and obtains competitive results even with a single input view. We also assess the transfer learning capabilities of the model by testing it against the publicly available Shelf dataset obtaining good performance metrics. The proposed method is inherently efficient: as a pure bottom-up approach, it is computationally independent of the number of people in the scene. Furthermore, even though the computational burden of the 2D part scales linearly with the number of input views, the overall architecture is able to exploit a very lightweight 2D backbone which is orders of magnitude faster than the volumetric counterpart, resulting in fast inference time. The system can run at 6 FPS, processing up to 10 camera views on a single 1080Ti GPU. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|