English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Existing 3D human pose estimation algorithms trained on distortion-freedatasets suffer performance drop when applied to new scenarios with a specificcamera distortion. In this paper, we propose a simple yet effective model for3D human pose estimation in video that can quickly adapt to any distortionenvironment by utilizing MAML, a representative optimization-basedmeta-learning algorithm. We consider a sequence of 2D keypoints in a particulardistortion as a single task of MAML. However, due to the absence of alarge-scale dataset in a distorted environment, we propose an efficient methodto generate synthetic distorted data from undistorted 2D keypoints. For theevaluation, we assume two practical testing situations depending on whether amotion capture sensor is available or not. In particular, we propose InferenceStage Optimization using bone-length symmetry and consistency. Extensiveevaluation shows that our proposed method successfully adapts to variousdegrees of distortion in the testing phase and outperforms the existingstate-of-the-art approaches. The proposed method is useful in practice becauseit does not require camera calibration and additional computations in a testingset-up.

Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning