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

We explore long-term temporal visual correspondence-based optimization for 3Dvideo object detection in this work. Visual correspondence refers to one-to-onemappings for pixels across multiple images. Correspondence-based optimizationis the cornerstone for 3D scene reconstruction but is less studied in 3D videoobject detection, because moving objects violate multi-view geometryconstraints and are treated as outliers during scene reconstruction. We addressthis issue by treating objects as first-class citizens duringcorrespondence-based optimization. In this work, we propose BA-Det, anend-to-end optimizable object detector with object-centric temporalcorrespondence learning and featuremetric object bundle adjustment.Empirically, we verify the effectiveness and efficiency of BA-Det for multiplebaseline 3D detectors under various setups. Our BA-Det achieves SOTAperformance on the large-scale Waymo Open Dataset (WOD) with only marginalcomputation cost. Our code is available athttps://github.com/jiaweihe1996/BA-Det.

3D Video Object Detection with Learnable Object-Centric Global Optimization