Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (1) · 1296-1304
DOI: 10.1609/aaai.v37i1.25213 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Han Li und 9 weiteren Autor:innen. Die Arbeit wurde bisher 80-mal zitiert (Crossref).
Abstract (Originalsprache)
There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies. However, existing transformer-based methods treat body joints as equally important inputs and ignore the prior knowledge of human skeleton topology in the self-attention mechanism. To tackle this issue, in this paper, we propose a Pose-Oriented Transformer (POT) with uncertainty guided refinement for 3D HPE. Specifically, we first develop novel pose-oriented self-attention mechanism and distance-related position embedding for POT to explicitly exploit the human skeleton topology. The pose-oriented self-attention mechanism explicitly models the topological interactions between body joints, whereas the distance-related position embedding encodes the distance of joints to the root joint to distinguish groups of joints with different difficulties in regression. Furthermore, we present an Uncertainty-Guided Refinement Network (UGRN) to refine pose predictions from POT, especially for the difficult joints, by considering the estimated uncertainty of each joint with uncertainty-guided sampling strategy and self-attention mechanism. Extensive experiments demonstrate that our method significantly outperforms the state-of-the-art methods with reduced model parameters on 3D HPE benchmarks such as Human3.6M and MPI-INF-3DHP.
Zitieren
APA
Li, H., Shi, B., Dai, W., Zheng, H., Wang, B., Sun, Y., Guo, M., Li, C., Zou, J., & Xiong, H. (2023). Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 1296-1304. https://doi.org/10.1609/aaai.v37i1.25213
Vancouver
Li H, Shi B, Dai W, Zheng H, Wang B, Sun Y, et al. Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(1):1296-1304. doi:10.1609/aaai.v37i1.25213
BibTeX
@article{Li2023,
author = {Li, Han and Shi, Bowen and Dai, Wenrui and Zheng, Hongwei and Wang, Botao and Sun, Yu and Guo, Min and Li, Chenglin and Zou, Junni and Xiong, Hongkai},
title = {Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {1},
pages = {1296--1304},
doi = {10.1609/aaai.v37i1.25213}
}
EUVIMED