Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry
This addresses the problem of reducing annotation costs for 3D human pose estimation in computer vision, though it is incremental as it builds on existing self-supervised and multi-view techniques.
The paper tackles 3D human pose estimation without ground-truth labels by using a self-supervised method with multiple-view geometry and a four-loss function algorithm, achieving performance that outperforms other self-supervised methods and is comparable to supervised approaches on benchmarks like Human3.6M.
We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view. To train our model, represented by a deep neural network, we propose a four-loss function learning algorithm, which does not require any 2D or 3D body pose ground-truth. The proposed loss functions make use of the multiple-view geometry to reconstruct 3D body pose estimates and impose body pose constraints across the camera views. Our approach utilizes all available camera views during training, while the inference is single-view. In our evaluations, we show promising performance on Human3.6M and HumanEva benchmarks, while we also present a generalization study on MPI-INF-3DHP dataset, as well as several ablation results. Overall, we outperform all self-supervised learning methods and reach comparable results to supervised and weakly-supervised learning approaches. Our code and models are publicly available