A Survey of Recent Advances on Two-Step 3D Human Pose Estimation

Manesco, João Renato Ribeiro; Marana, Aparecido Nilceu

doi:10.1007/978-3-031-21689-3_20

Cited by 1 publication

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent works started to notice the discrepancy in performance between data obtained from distinct distributions [20]. To deal with this issue, several approaches have been proposed, such as that in [21], where synthetic pose datasets artificially generated were used to enhance the amount of data available during the training.…”

Section: Cross-domain 3d Human Pose Estimationmentioning

confidence: 99%

DUA: A Domain-Unified Approach for Cross-Dataset 3D Human Pose Estimation

Manesco,

Berretti,

Marana

2023

Sensors

View full text Add to dashboard Cite

Human pose estimation is an important Computer Vision problem, whose goal is to estimate the human body through joints. Currently, methods that employ deep learning techniques excel in the task of 2D human pose estimation. However, the use of 3D poses can bring more accurate and robust results. Since 3D pose labels can only be acquired in restricted scenarios, fully convolutional methods tend to perform poorly on the task. One strategy to solve this problem is to use 2D pose estimators, to estimate 3D poses in two steps using 2D pose inputs. Due to database acquisition constraints, the performance improvement of this strategy can only be observed in controlled environments, therefore domain adaptation techniques can be used to increase the generalization capability of the system by inserting information from synthetic domains. In this work, we propose a novel method called Domain Unified approach, aimed at solving pose misalignment problems on a cross-dataset scenario, through a combination of three modules on top of the pose estimator: pose converter, uncertainty estimator, and domain classifier. Our method led to a 44.1mm (29.24%) error reduction, when training with the SURREAL synthetic dataset and evaluating with Human3.6M over a no-adaption scenario, achieving state-of-the-art performance.

show abstract

Section: Cross-domain 3d Human Pose Estimationmentioning

confidence: 99%