Hai Ci*, Mickel Liu*, Xuehai Pan*, Fangwei Zhong, Yizhou Wang
*Equal Contribution
Peking University & Beijing Institute of General Artificial Intelligence (BIGAI)
International Conference on Learning Representations (ICLR) 2023
Dynamic Occlusions lead to failed pose estimations
Fixed-Cameras cannot mo-cap unconstrained target
A failure case for 5 fixed-camera baseline
ICLR 2023 Paper 1361 Demo - UnrealPose.mp4ICLR 2023 Paper 1361 - Visualization Tool.mp4ICLR 2023 Paper 1361 Demo Video.mp4school_gym_test_demo.mp4building.mp4ICLR 2023 Paper 1361 Demo - Fixed-Cameras Pentagon Formation.mp4ICLR 2023 Paper 1361 Demo - MAPPO Baseline.mp4
The CTCR is incentivized by the concept of Shapley Value. The r-function in the above equation is the accuracy of the triangulated human pose. In essence, CTCR measures the average weighted marginal contribution of a camera agent to every valid sub-formation that contains this agent. A sub-formation needs to have at least two cameras to be considered valid, since the problem definition requires at least two cameras to form a valid multi-view 3D triangulation.
The main idea is that achieving the overall optimality needs to also account for the optimality of every possible sub-formation (S). In order for a camera agent to receive the highest reward possible, its current position and view must be optimal both in terms of its current formation and any sub-formation possible.
The figure below shows an example of calculating CTCR for every camera agent in a three-cameras team.
Below shows the loss equations for these five WDL objectives: (Full psuedo-code refers to Apendix A)
@inproceedings{
ci2023proactive,
title={Proactive Multi-Camera Collaboration for 3D Human Pose Estimation},
author={Hai Ci and Mickel Liu and Xuehai Pan and fangwei zhong and Yizhou Wang},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=CPIy9TWFYBG}
}