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

Deducing a 3D human pose from a single 2D image or 2D keypoints is inherentlychallenging, given the fundamental ambiguity wherein multiple 3D poses cancorrespond to the same 2D representation. The acquisition of 3D data, whileinvaluable for resolving pose ambiguity, is expensive and requires an intricatesetup, often restricting its applicability to controlled lab environments. Weimprove performance of monocular human pose estimation models using multiviewdata for fine-tuning. We propose a novel loss function, multiview consistency,to enable adding additional training data with only 2D supervision. This lossenforces that the inferred 3D pose from one view aligns with the inferred 3Dpose from another view under similarity transformations. Our consistency losssubstantially improves performance for fine-tuning with no available 3D data.Our experiments demonstrate that two views offset by 90 degrees are enough toobtain good performance, with only marginal improvements by adding more views.Thus, we enable the acquisition of domain-specific data by capturing activitieswith off-the-shelf cameras, eliminating the need for elaborate calibrationprocedures. This research introduces new possibilities for domain adaptation in3D pose estimation, providing a practical and cost-effective solution tocustomize models for specific applications. The used dataset, featuringadditional views, will be made publicly available.

Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistency