In contrast, 3d pose estimation from a single image is ill-posed due to occlusion and depth ambiguities.

This paper focuses on the problem of 3D human pose reconstruction from multiple viewpoints in video sequences. The system assumes that a set of 2D human poses are available (e.g. by using OpenPose), coming from different camera viewpoints, and the paper proposes a pipeline for simultaneously selecting the next viewpoint that would be needed to decrease the reconstruction error and generating the 3D reconstruction. An artificial agent, named ACTOR, is defined for the purpose of selecting the camera viewpoints, following a reward-based approach. The proposed system is evaluated on the CMU Panoptic dataset, which contains 480 VGA camera views. The experimental results show that by using the proposed agent the reconstruction error is better than using the baseline methods. The remaining components of the system do not seem to be novel.

This paper presents a method based on agent to select the best view for a 3D pose estimation given 2D poses available. The proposed system is evaluated on the CMU Panoptic dataset, which contains 480 VGA camera views. The reviewers agree with the originaly of the task and the proposal and on the clearness of the presentation Rebuttal was convincing and thus also the area chair agrees for an acceptance of the paper.

Existing state-of-the-art estimation systems can detect 2d poses of multiple people in images quite reliably. In contrast, 3d pose estimation from a single image is ill-posed due to occlusion and depth ambiguities. Assuming access to multiple cameras, or given an active system able to position itself to observe the scene from multiple viewpoints, reconstructing 3d pose from 2d measurements becomes well-posed within the framework of standard multi-view geometry. Less clear is what is an informative set of viewpoints for accurate 3d reconstruction, particularly in complex scenes, where people are occluded by others or by scene objects. In order to address the view selection problem in a principled way, we here introduce ACTOR, an active triangulation agent for 3d human pose reconstruction.

Existing state-of-the-art estimation systems can detect 2d poses of multiple people in images quite reliably. In contrast, 3d pose estimation from a single image is ill-posed due to occlusion and depth ambiguities. Assuming access to multiple cameras, or given an active system able to position itself to observe the scene from multiple viewpoints, reconstructing 3d pose from 2d measurements becomes well-posed within the framework of standard multi-view geometry. Less clear is what is an informative set of viewpoints for accurate 3d reconstruction, particularly in complex scenes, where people are occluded by others or by scene objects. In order to address the view selection problem in a principled way, we here introduce ACTOR, an active triangulation agent for 3d human pose reconstruction.