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

The recovery of 3D human mesh from monocular images has significantly beendeveloped in recent years. However, existing models usually ignore spatial andtemporal information, which might lead to mesh and image misalignment andtemporal discontinuity. For this reason, we propose a novel Spatio-TemporalAlignment Fusion (STAF) model. As a video-based model, it leverages coherenceclues from human motion by an attention-based Temporal Coherence Fusion Module(TCFM). As for spatial mesh-alignment evidence, we extract fine-grained localinformation through predicted mesh projection on the feature maps. Based on thespatial features, we further introduce a multi-stage adjacent Spatial AlignmentFusion Module (SAFM) to enhance the feature representation of the target frame.In addition to the above, we propose an Average Pooling Module (APM) to allowthe model to focus on the entire input sequence rather than just the targetframe. This method can remarkably improve the smoothness of recovery resultsfrom video. Extensive experiments on 3DPW, MPII3D, and H36M demonstrate thesuperiority of STAF. We achieve a state-of-the-art trade-off between precisionand smoothness. Our code and more video results are on the project pagehttps://yw0208.github.io/staf/

STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion