paper-with-me

홈 › Papers

How Robust is 3D Human Pose Estimation to Occlusion?

2018-08-28 · István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe

Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks. This leaves the question open: how robust are state-of-the-art 3D pose estimation methods against partial occlusions? We study several types of synthetic occlusions over the Human3.6M dataset and find a method with state-of-the-art benchmark performance to be sensitive even to low amounts of occlusion. Addressing this issue is key to progress in applications such as collaborative and service robotics. We take a first step in this direction by improving occlusion-robustness through training data augmentation with synthetic occlusions. This also turns out to be an effective regularizer that is beneficial even for non-occluded test cases.

📄 PDF Abstract BibTeX arXiv:1808.09316

Code (2)

isarandi/synthetic-occlusion
laurabragagnolo/human3.6m-occluded

Tasks

3D Human Pose Estimation3D Pose EstimationData AugmentationPose Estimation

Similar Papers 제목 키워드 기반

Beyond Tree Structure Models: A New Occlusion Aware Graphical Model for Human Pose Estimation

2015-12-01 · ICCV 2015 12 · Lianrui Fu, Junge Zhang, Kaiqi Huang

Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structure models. The tree structure model is simple and convenient for exact inference, but short in modeling the occlusi…

2D Human Pose EstimationPose Estimation

Tilting at windmills: Data augmentation for deep pose estimation does not help with occlusions

2020-10-20 · Rafal Pytel, Osman Semih Kayhan, Jan C. van Gemert

Occlusion degrades the performance of human pose estimation. In this paper, we introduce targeted keypoint and body part occlusion attacks. The effects of the attacks are systematically analyzed on the best performing me…

Data AugmentationPose Estimation

LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering

2021-08-01 · Kaibing Yang, Renshu Gu, Maoyu Wang, Masahiro Toyoura 외

A key challenge in the task of human pose and shape estimation is occlusion, including self-occlusions, object-human occlusions, and inter-person occlusions. The lack of diverse and accurate pose and shape training data …

3D Human Pose Estimation3D Human Shape EstimationPose Estimation

Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose Estimation

2024-08-28 · Laura Bragagnolo, Matteo Terreran, Davide Allegro, Stefano Ghidoni

Robust 3D human pose estimation is crucial to ensure safe and effective human-robot collaboration. Accurate human perception,however, is particularly challenging in these scenarios due to strong occlusions and limited ca…

3D Human Pose Estimation3D Pose EstimationPose Estimation

Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation

2022-07-29 · Qihao Liu, Yi Zhang, Song Bai, Alan Yuille

Occlusion poses a great threat to monocular multi-person 3D human pose estimation due to large variability in terms of the shape, appearance, and position of occluders. While existing methods try to handle occlusion with…

3D Human Pose Estimation3D Multi-Person Pose Estimation (absolute)3D Multi-Person Pose Estimation (root-relative)Data Augmentation+1